IP Library › Granted Patent US 12,400,422
Granted Patent B2
US 12,400,422 · App. 17/820,946 · Granted Aug 26, 2025

Sensor fusion approach for plastics identification

Inventors: Gearoid Murphy (Mountain View, CA); Alexander Holiday (Brookfield, WI); Diosdado Banatao (Los Altos Hills, CA); Allen Zhao (Mountain View, CA); Shruti Badhwar (San Mateo, CA)
Assignee: X Development LLC
G06V10/58G01J3/2823G01J3/40G06V10/56G06V10/774G06V10/806G06V20/64G01J2003/2826
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,400,422
App. No.
17/820,946
Granted
Aug 26, 2025
Kind
B2
Abstract

Methods and systems for using multiple hyperspectral cameras sensitive to different wavelengths to predict characteristics of objects for further processing, including recycling, are described. The multiple hyperspectral images can be used to predict higher resolution spectra by using a trained machine learning model. The higher resolution spectra may be more easily analyzed to sort plastics into a recyclability category. The hyperspectral images may also be used to identify and analyze dark or black plastics, which are challenging for SWIR, MWIR, and other wavelengths. The machine learning model may also predict the base polymers and contaminants of plastic objects for recycling. The hyperspectral images may be used to predict recyclability and other characteristics using a trained machine learning model.

Claims (54)

1. A method comprising:

accessing a set of location-specific spectra, wherein each location-specific spectrum in the set of location-specific spectra characterizes an extent to which electromagnetic radiation at each of a first set of frequency bands was reflected by a material located at a physical location corresponding to the location-specific spectrum;

accessing a hyperspectral image of one or more objects in a region of a conveyor belt that includes a plurality of physical locations corresponding to the set of location-specific spectra;

generating one or more predicted characteristics of the one or more objects within the region by processing the set of location-specific spectra and the hyperspectral image in parallel using a machine learning model; and

outputting the one or more predicted characteristics, wherein the predicted characteristics include a base polymer composition of each of the one or more objects.

2. The method of claim 1 , further comprising:

generating a first hypercube that includes the set of location-specific spectra, wherein:

each of a first dimension and a second dimension of the first hypercube correspond to a dimension in physical space, and

a third dimension of the first hypercube corresponds to the first set of frequency bands; and

generating a second hypercube using the hyperspectral image, wherein:

each of a first dimension and a second dimension of the second hypercube correspond to a dimension in physical space,

a third dimension of the second hypercube corresponds to a second set of frequency bands, and

processing the set of location-specific spectra and the hyperspectral image in parallel includes processing the first hypercube and the second hypercube.

3. The method of claim 1 , wherein the one or more predicted characteristics further includes a prediction as to whether the one or more objects are black.

4. The method of claim 1 , wherein the one or more predicted characteristics further includes a prediction of a suitability of the material of the one or more objects for polyolefin-class chemical recycling.

5. The method of claim 1 , wherein the one or more predicted characteristics further include a predicted higher resolution spectrum that has smaller frequency bands as compared to the first set of frequency bands.

6. The method of claim 1 , wherein:

the one or more predicted characteristics includes multiple characteristics,

the machine learning model was trained using multiple loss functions, and

each of the multiple loss functions depends on an accuracy of the one or more predicted characteristics.

7. The method of claim 1 , wherein the machine learning model includes multiple two-dimensional convolutional layers.

8. The method of claim 1 , wherein the machine learning model further includes at least one fully connected dense layer.

9. The method of claim 1 , wherein the machine learning model further includes at least one max pooling layer.

10. The method of claim 1 , wherein the set of location-specific spectra includes a set of mid-wave infrared radiation spectra.

11. The method of claim 1 , wherein the set of location-specific spectra includes a set of small wave infrared radiation spectra.

12. The method of claim 1 , wherein the set of location specific spectra and the hyperspectral image were collected at a system that includes a first camera sensitive to short-wave infrared radiation, a second camera sensitive to mid-wave infrared radiation, and the conveyor belt configured to move the one or more objects.

13. The method of claim 1 , wherein the set of location-specific spectra includes a set of spectra from 300 nm to 1,000 nm.

14. A computer-program product tangibly embodied in a non-transitory machine-readable storage medium, including instructions configured to cause one or more data processors to perform a method comprising:

accessing a set of location-specific spectra, wherein each location-specific spectrum in the set of location-specific spectra characterizes an extent to which electromagnetic radiation at each of a first set of frequency bands was reflected by a material located at a physical location corresponding to the location-specific spectrum;

accessing a hyperspectral image of one or more objects in a region of a conveyor belt that includes a plurality of physical locations corresponding to the set of location-specific spectra;

generating one or more predicted characteristics of the one or more objects within the region by processing the set of location-specific spectra and the hyperspectral image in parallel using a machine learning model; and

outputting the one or more predicted characteristics, wherein the predicted characteristics include a base polymer composition of each of the one or more objects.

15. The computer-program product of claim 14 , the method further comprising:

generating a first hypercube that includes the set of location-specific spectra, wherein:

each of a first dimension and a second dimension of the first hypercube correspond to a dimension in physical space, and

a third dimension of the first hypercube corresponds to the first set of frequency bands; and

generating a second hypercube using the hyperspectral image, wherein:

each of a first dimension and a second dimension of the second hypercube correspond to a dimension in physical space,

a third dimension of the second hypercube corresponds to a second set of frequency bands, and

processing the set of location-specific spectra and the hyperspectral image in parallel includes processing the first hypercube and the second hypercube.

16. The computer-program product of claim 14 , wherein the one or more predicted characteristics further include a predicted higher resolution spectrum that has smaller frequency bands as compared to the first set of frequency bands.

17. A system comprising:

one or more data processors; and

a non-transitory computer readable storage medium containing instructions which, when executed on the one or more data processors, cause the one or more data processors to perform a method comprising:

accessing a set of location-specific spectra, wherein each location-specific spectrum in the set of location-specific spectra characterizes an extent to which electromagnetic radiation at each of a first set of frequency bands was reflected by a material located at a physical location corresponding to the location-specific spectrum;

accessing a hyperspectral image of one or more objects in a region of a conveyor belt that includes a plurality of physical locations corresponding to the set of location-specific spectra;

generating one or more predicted characteristics of the one or more objects within the region by processing the set of location-specific spectra and the hyperspectral image in parallel using a machine learning model; and

outputting the one or more predicted characteristics, wherein the predicted characteristics include a base polymer composition of each of the one or more objects.

18. The system of claim 17 , further comprising:

a first camera sensitive to short-wave infrared radiation,

a second camera sensitive to mid-wave infrared radiation, and

the conveyor belt configured to move the one or more objects.

19. The system of claim 18 , further comprising:

a third camera sensitive to visible and near infrared light.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 27, 2022
From: MURPHY, GEAROID; HOLIDAY, ALEXANDER; BANATAO, DIOSDADO; ZHAO, ALLEN; BADHWAR, SHRUTI
To: X DEVELOPMENT LLC
Reel/Frame 061559/0170 →
Continuity (2)
Provisional Application 63236967 · Aug 25, 2021
Related Publication 20230062938A1 · Mar 2, 2023
References Cited (144)
US 5040229A · Lee et al. · 1991 [cited by applicant]
US 5835633A · Fujisaki et al. · 1998 [cited by applicant]
US 7840071B2 · Tang et al. · 2010 [cited by applicant]
US 8164673B2 · Horie · 2012 [cited by applicant]
US 8284991B2 · Tojo et al. · 2012 [cited by applicant]
US 8406469B2 · Fisher · 2013 [cited by applicant]
US 8860942B1 · Ewing et al. · 2014 [cited by applicant]
US 9107624B2 · Darty · 2015 [cited by applicant]
US 9251431B2 · Doepke et al. · 2016 [cited by applicant]
US 9268110B2 · Bueler et al. · 2016 [cited by applicant]
US 9945721B2 · Abolbashari et al. · 2018 [cited by applicant]
US 10013760B2 · Bhargava · 2018 [cited by applicant]
US 10452924B2 · Adato et al. · 2019 [cited by applicant]
US 10453197B1 · Cholakkal et al. · 2019 [cited by applicant]
US 10515715B1 · Pappas et al. · 2019 [cited by applicant]
US 10520482B2 · McPeek · 2019 [cited by applicant]
US 10810723B2 · Onoro-Rubio et al. · 2020 [cited by applicant]
US 20080118106A1 · Kilambi et al. · 2008 [cited by applicant]
US 20140122044A1 · Yasukawa · 2014 [cited by applicant]
US 20150021478A1 · Lee et al. · 2015 [cited by applicant]
US 20160358027A1 · Hotta et al. · 2016 [cited by applicant]
US 20170147905A1 · Huang et al. · 2017 [cited by applicant]
US 20170316285A1 · Ahmed et al. · 2017 [cited by applicant]
US 20180284273A1 · Buettgen et al. · 2018 [cited by applicant]
US 20180349770A1 · Nelson et al. · 2018 [cited by applicant]
US 20190026586A1 · Liu et al. · 2019 [cited by applicant]
US 20190065880A1 · Loginov et al. · 2019 [cited by applicant]
US 20190139193A1 · Navarrete Michelini et al. · 2019 [cited by applicant]
US 20190180153A1 · Buckler et al. · 2019 [cited by applicant]
US 20190205643A1 · Liu et al. · 2019 [cited by applicant]
US 20200237229A1 · Fei · 2020 [cited by examiner]
US 20220161298A1 · Kumar · 2022 [cited by examiner]
US 20230053268A1 · Garcia, Jr. · 2023 [cited by examiner]
US 20230120932A1 · Parr · 2023 [cited by examiner]
US 20240074664A1 · Fei · 2024 [cited by examiner]
AU 2014292179 · 2015 [cited by applicant]
CN 102289673 · 2011 [cited by applicant]
CN 103942562 · 2014 [cited by applicant]
CN 104050677 · 2014 [cited by applicant]
CN 104077613 · 2014 [cited by applicant]
CN 104732240 · 2015 [cited by applicant]
CN 105528589 · 2016 [cited by applicant]
CN 108921822 · 2018 [cited by applicant]
CN 110084311 · 2019 [cited by applicant]
CN 108052984 · 2019 [cited by applicant]
CN 110647793 · 2020 [cited by applicant]
EP 2208974 · 2010 [cited by applicant]
EP 2942615 · 2015 [cited by applicant]
EP 3567518 · 2019 [cited by applicant]
WO 0169191 · 2001 [cited by applicant]
WO 2007098123 · 2007 [cited by applicant]
WO 2015007697 · 2015 [cited by applicant]
WO 2016095117 · 2016 [cited by applicant]
WO 2017130249 · 2017 [cited by applicant]
WO 2017223206 · 2017 [cited by applicant]
WO 2018141429 · 2018 [cited by applicant]
WO 2018187632 · 2018 [cited by applicant]
WO 2019084854 · 2019 [cited by applicant]
WO 2019178561 · 2019 [cited by applicant]
WO 2022170273A1 · 2022 [cited by applicant]
N. Audebert, B. Le Saux and S. Lefevre, “Deep Learning for Classification of Hyperspectral Data: A Comparative Review,” in IEEE Geoscience and Remote Sensing Magazine, vol. 7, No. 2, pp. 159-173, Jun. 2019, doi: 10.1109… [cited by examiner]
Niedermaier et al., Quantification and Classification in Process Analytics using Hyperspectral Imaging, Proceedings of SPIE, vol. 11144, Sep. 2019, pp. 1114409-1-1114409-11. [cited by applicant]
International Application No. PCT/US2022/041045, International Search Report and Written Opinion mailed on Nov. 11, 2022, 14 pages. [cited by applicant]
Signoret et al., MIR Spectral Characterization of Plastic to Enable Discrimination in an Industrial Recycling Context: II. Specific Case of Polyolefins, Waste Management, vol. 98, Oct. 2019, pp. 160-172. [cited by applicant]
Brix, Available Online at: https://en.wikipedia.org/wiki/Brix, Accessed from Internet on Sep. 23, 2021, 4 pages. [cited by applicant]
Chemical Detection, Teledyne FLIR, Available Online at: https://www.flir.com/threat-detection/chemical/, 2021, 3 pages. [cited by applicant]
Chemometrics, Available Online at: https://en.wikipedia.org/wiki/Chemometrics, Accessed from Internet on Sep. 23, 2021, 7 pages. [cited by applicant]
MobileNet V2, Pytorch Team, Available Online at: https://pytorch.org/hub/pytorch_vision_mobilenet_v2/, Accessed from Internet on Sep. 23, 2021, 2 pages. [cited by applicant]
MobileNetV2: The Next Generation of On-Device Computer Vision Networks, Google AI Blog, Available Online at: http://ai.googleblog.com/2018/04/mobilenetv2-next-generation-of-on.html, Apr. 3, 2018, 3 pages. [cited by applicant]
Optical Gas Imaging for the Chemical Industry, Flir.com, Available Online at: https://www.flir.in/discover/instruments/gas-detection/optical-gas-imaging-for-the-chemical-industry/, Aug. 2021, 5 pages. [cited by applicant]
Optical Sorting, Available Online at: https://en.wikipedia.org/wiki/Optical_sorting, Accessed from Internet on Sep. 23, 2021, 7 pages. [cited by applicant]
Resnet101, MathWorks, Available Online at: https://www.mathworks.com/help/deeplearning/ref/resnet101.html;jsessionid=1a374f68ed8d150528c1ba657502, Oct. 24, 2018, 3 pages. [cited by applicant]
Tensorflow Count Objects in Image, Available online at: https://stackoverflow.com/questions/42375680/tensorflowcount-objects-in-image, Feb. 21, 2017, 2 pages. [cited by applicant]
The Ins and Outs of Using Post-Consumer Resin in Packaging, Canadian Plastics, Available Online at: https://www.canplastics.com/features/the-ins-and-outs-of-using-post-consumer-resin-in-packaging/, May 6, 2021, 4 pages. [cited by applicant]
Akai et al., Distortion-Adaptive Grape Bunch Counting for Omnidirectional Images, 25th International Conference on Pattern Recognition (ICPR) Available Online at: https://arxiv.org/pdf/2008.12511.pdf, Aug. 28, 2020, 8 p… [cited by applicant]
Alam et al., CRF Learning with CNN Features for Hyperspectral Image Segmentation, IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Jul. 10-15, 2016, 5 pages. [cited by applicant]
Annibale et al., Optical Measurement of Focal Offset in Tunable Lenses, Optics Express, vol. 24, No. 2, Jan. 25, 2016, pp. 1031-1036. [cited by applicant]
Barbin et al., Near-Infrared Hyperspectral Imaging for Grading and Classification of Pork, Meat Science, vol. 90, No. 1, Jan. 2012, pp. 259-268. [cited by applicant]
Bargoti et al., Deep Fruit Detection in Orchards, IEEE International Conference on Robotics and Automation (ICRA), May 29-Jun. 3, 2017, pp. 3626-3633. [cited by applicant]
Baweja et al., StalkNet: A Deep Learning Pipeline for High-Throughput Measurement of Plant Stalk Count and Stalk Width, Field and Service Robotics, Nov. 2017, pp. 271-284. [cited by applicant]
Bonus et al., Objects Counting by Estimating a Density Map with Convolutional Neural Networks, Available Online at: https://towardsdatascience.com/objects-counting-by-estimating-a-density-map-with-convolutional-neural-n… [cited by applicant]
Brownlee, How to Configure Image Data Augmentation in Keras, Machine Learning Mastering, Available Online at: https://machinelearningmastery.com/how-to-configure-image-data-augmentation-when-training-deep-learning-neura… [cited by applicant]
Chen et al., Predicting the Anthocyanin Content of Wine Grapes by NIR Hyperspectral Imaging, Food Chemistry, vol. 172, Apr. 1, 2015, pp. 788-793. [cited by applicant]
Cohen et al., Count-ception: Counting by Fully Convolutional Redundant Counting, Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 18-26. [cited by applicant]
Culurciello, Segmenting, Localizing and Counting Object Instances in an Image, Available Online at: https://towardsdatascience.com/segmenting-localizing-and-counting-object-instances-in-an-image-878805fef7fc, Oct. 26, 2… [cited by applicant]
Cu-Nguyen et al., An Imaging Spectrometer Employing Tunable Hyperchromatic Microlenses, Light: Science & Applications, vol. 5, No. 4, Apr. 8, 2016, 9 pages. [cited by applicant]
Cu-Nguyen et al., Tunable Hyperchromatic Lens System for Confocal Hyperspectral Sensing, Optics Express, vol. 21, No. 23, Nov. 18, 2013, pp. 27611-27621. [cited by applicant]
Dahab et al., Automated Brain Tumor Detection and Identification Using Image Processing and Probabilistic Neural Network Techniques, International Journal of Image Processing and Visual Communication, vol. 1, No. 2, Oct… [cited by applicant]
Elmasry et al., Chemical-Free Assessment and Mapping of Major Constituents in Beef Using Hyperspectral Imaging, Journal of food Engineering, vol. 117, No. 2, Jul. 2013, pp. 235-246. [cited by applicant]
Gandhi, R-CNN, Fast R-CNN, Faster R-CNN, YOLO—Object Detection Algorithms, Towardsdatascience.com, Available Online at: https://towardsdatascience.com/r-cnn-fast-r-cnn-faster-r-cnn-yolo-object-detection-algorithms-36d53… [cited by applicant]
Gao et al., Counting Dense Objects in Remote Sensing Images, CoRR, Available Online at: https://arxiv.org/pdf/2002.05928.pdf, Feb. 14, 2020, 5 pages. [cited by applicant]
Gao et al., Intra-Ensemble in Neural Networks, CoRR, Available Online at: https://arxiv.org/pdf/1904.04466v1.pdf, Apr. 9, 2019, 11 pages. [cited by applicant]
Gao et al., PSCNet: Pyramidal Scale and Global Context Guided Network for Crowd Counting, CoRR, Available Online at: https://arxiv.org/pdf/2012.03597v1.pdf, Dec. 7, 2020, 11 pages. [cited by applicant]
Gat, Imaging Spectroscopy Using Tunable Filters: A Review, Proceedings of SPIE—The International Society for Optical Engineering, vol. 4056, No. 1, Apr. 2000, pp. 50-64. [cited by applicant]
Godi et al., SIMCO: SIMilarity-Based Object Counting, CoRR, Available Online at: https://arxiv.org/pdf/1904.07092.pdf, Oct. 13, 2020, 6 pages. [cited by applicant]
Goel et al., Low-Power Object Counting with Hierarchical Neural Networks, CoRR, Available Online at: https://arxiv.org/pdf/2007.01369.pdf, Jul. 2, 2020, 6 pages. [cited by applicant]
Gomez-Sanchis et al., Hyperspectral System for Early Detection of Rottenness Caused by Penicillium Digitatum in Mandarins, Journal of food Engineering, vol. 89, No. 1, Apr. 2008, pp. 80-86. [cited by applicant]
Gomez-Sanchis et al., Segmentation of Hyperspectral Images for the Detection of Rotten Mandarins, International Conference Image Analysis and Recognition, Jun. 2008, 2 pages. [cited by applicant]
Grajek, Counting Objects with Faster R-CNN, softwaremill.com, Available Online at: https://softwaremill.com/counting-objects-with-faster-rcnn/, Jun. 2, 2017, 20 pages. [cited by applicant]
Guan et al., Understanding the Ability of Deep Neural Networks to Count Connected Components in Images, CoRR, Available Online at: https://arxiv.org/pdf/2101.01386.pdf, Jan. 5, 2021, 7 pages. [cited by applicant]
Gupta et al., Hyperspectral Imaging Using Acoustic-Optic Tunable Filters, Part of the SPIE Conference on Automatic Target Recognition IX, vol. 3718, Apr. 1999, pp. 512-521. [cited by applicant]
Habermann et al., Supervised Band Selection in Hyperspectral Images Using Single-Layer Neural Networks, International Journal of Remote Sensing, vol. 40, No. 10, Dec. 2018, pp. 1-27. [cited by applicant]
Habermann et al., Unsupervised Hyperspectral Band Selection using Clustering and Single-Layer Neural Network, Revue Francaise de Photogrammetrie et de Teledetection, Societe Frarwaise de Photogrammetrie et de Teledetect… [cited by applicant]
Halstead et al., Fruit Quantity and Quality Estimation using a Robotic Vision System, CoRR, Available Online at: https://arxiv.org/pdf/1801.05560.pdf, Jan. 17, 2018, 8 pages. [cited by applicant]
Hani et al., Apple Counting using Convolutional Neural Networks, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Oct. 2018, pp. 2559-2564. [cited by applicant]
Hu et al., Deep Convolutional Neural Networks for Hyperspectral Image Classification, Journal of Sensors, vol. 2015, Jul. 30, 2015, 13 pages. [cited by applicant]
Islam et al., Detection of Potato Diseases Using Image Segmentation and Multiclass Support Vector Machine, IEEE 30th Canadian Conference on Electrical and Computer Engineering (CCECE), Apr. 2017, pp. 30-33. [cited by applicant]
Iwai et al., Speeded-Up Focus Control of Electrically Tmrnble Lens by Sparse Optimization, Scientific Reports, vol. 9, No. 12365, Aug. 26, 2019, pp. 1-6. [cited by applicant]
Kahveci, How to Count Objects on the Image with Deep Learning Algorithms? Available Online at: https://www.researchgate.net/post/How-to-count-objects-on-the-image-with-deep-learning-algorithms, Apr. 30. 2020, 9 pages. [cited by applicant]
Kamruzzaman et al., Non-Destructive Prediction and Visualization of Chemical Composition in Lamb Meat Using NIR Hyperspectral Imaging and Multivariate Regression, Innovative Food Science & Emerging Technologies, vol. 16… [cited by applicant]
Kasmani et al., A-CCNN: Adaptive CCNN for Density Estimation and Crowd Counting, CoRR, Available Online at: https://arxiv.org/pdf/1804.06958.pdf, Apr. 20, 2018, 5 pages. [cited by applicant]
Kemker et al., Algorithms for Semantic Segmentation of Multispectral Remote Sensing Imagery Using Deep Learning, ISPRS Journal of Photogrammetry and Remote Sensing, Available Online at: https://arxiv.org/pdf/1703.06452.… [cited by applicant]
Koirala et al., Deep Learning for Real-Time Fruit Detection and Orchard Fruit Load Estimation: Benchmarking of 'Mango YOLO, Precision Agriculture, vol. 20, Feb. 28, 2019, pp. 1107-1135. [cited by applicant]
Lempitsky et al., Learning to Count Objects in Images, Advances in Neural Information Processing Systems, vol. 23, Dec. 2010, pp. 1-9. [cited by applicant]
Liu et al., Robust Fruit Counting: Combining Deep Learning, Tracking, and Structure from Motion, IEEE/RSJ International Conference on Intelligent Robots and Systems, Aug. 2018, 8 pages. [cited by applicant]
Lorenzo et al., Segmentation of Hyperspectral Images Using Quantized Convolutional Neural Networks, 21st Euromicro Conference on Digital System Design (DSD), Aug. 29-31, 2018, pp. 260-267. [cited by applicant]
Marsden et al., People, Penguins and Petri Dishes: Adapting Object Counting Models to New Visual Domains and Object Types without Forgetting, CoRR, Nov. 2017, pp. 8070-8079. [cited by applicant]
McGregor et al., Adaptive Hyperspectral Imager: Design, Modeling, and Control, Journal of Optics, vol. 17, No. 8, Aug. 2015, 11 pages. [cited by applicant]
Mikami et al., DeepCounter: Using Deep Leaning to Count Garbage Bags, IEEE 24th International Conference on Embedded and Real-Time Computing Systems and Applications (RTCSA), Jan. 9, 2019, 10 pages. [cited by applicant]
Millan et al., Dynamic Compensation of Chromatic Aberration in a Programmable Diffractive Lens, Optics Express, vol. 14, No. 20, Oct. 2006, pp. 9103-9112. [cited by applicant]
Nesteruk et al., Image Augmentation for Multitask Few-Shot Leaning: Agricultural Domain Use-Case, Available Online at: https://arxiv.org/pdf/2102.12295.pdf, Feb. 2021, 12 pages. [cited by applicant]
Noroozi et al., Representation Learning by Learning to Count, Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 5898-5906. [cited by applicant]
Rahnemoonfar et al., Deep Count: Fruit Counting Based on Deep Simulated Learning, Sensors, vol. 17, No. 4, Apr. 2017, 12 pages. [cited by applicant]
Sam et al., Switching Convolutional Neural Network for Crowd Counting, 2017 IEEE Conference on Computer Vision and Pattern Recognition, Jul. 2017, 9 pages. [cited by applicant]
Santos De Arruda et al., Counting and Locating High-Density Objects Using Convolutional Neural Network, CoRR, Available Online at https://arxiv.org/pdf/2102.04366.pdf, Feb. 8, 2021, 15 pages. [cited by applicant]
Segui et al., Learning to Count with Deep Object Features, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, May 2015, pp. 90-96. [cited by applicant]
Shang et al., End-to-End Crowd Counting via Joint Learning Local and Global Count, 2016 IEEE International Conference on Image Processing, Sep. 2016, pp. 1215-1219. [cited by applicant]
Sharma, It's a Record-Breaking Crowd! A Must-Read Tutorial to Build your First Crowd Counting Model using Deep Learning, Analytics Vidhya, Available Online at: https://www.analyticsvidhya.com/blog/2019/02/building-crowd… [cited by applicant]
Shen et al., Liquid Crystal Integrated Metalens with Tunable Chromatic Aberration, Advanced Photonics, vol. 2, No. 3, May-Jun. 2020, pp. 1-7. [cited by applicant]
Sokhandan et al., A Few-Shot Sequential Approach for Object Counting, CoRR, Available Online at: https://arxiv.org/pdf/2007.01899v2.pdf, Jul. 2020, 19 pages. [cited by applicant]
Stein et al., Image Based Mango Fruit Detection, Localization and Yield Estimation Using Multiple View Geometry, Sensors, vol. 16, No. 11, Nov. 2016, pp. 1-25. [cited by applicant]
Suzuki et al., Estimation of Chemical Composition of Grass in Meadows using Hyperspectral Imaging, Environmental Control in Biology, vol. 46, No. 2, Jan. 2008, pp. 129-137. [cited by applicant]
Takahashi et al., A Novel Weight-Shared Multi-Stage CNN for Scale Robustness, IEEE Transactions on Circuits and Systems for Video Technology, vol. 14, No. 8, Available Online at: https://arxiv.org/pdf/1702.03505.pdf, Au… [cited by applicant]
Tan et al., Cells Counting with Convolutional Neural Network, Intelligent Computing Methodologies, Jul. 2018, pp. 102-111. [cited by applicant]
Trajanovsk et al., Tumor Semantic Segmentation in Hyperspectral Images Using Deep Learning, International Conference on Medical Imaging with Deep Learning—Extended Abstract Track, Apr. 2019, 4 pages. [cited by applicant]
Walach et al., Learning to Count with CNN Boosting, Computer Vision, Sep. 2016, 17 pages. [cited by applicant]
Wang et al., Correcting Axial Chromatic Aberration in a Fixed Focal Plane, Near-Infrared Imaging System, CSBE/SCGAB Annual Conference, Jul. 16-19, 2006, 14 pages. [cited by applicant]
Xu et al., Dilated-Scale-Aware Attention ConvNet for Multi-Class Object Counting, CoRR, Available online at https://arxiv.org/pdf/2012.08149.pdf, Dec. 2020, 7 pages. [cited by applicant]
Yang et al., Reverse Perspective Network for Perspective-Aware Object Counting, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Jun. 2020, pp. 4374-4383. [cited by applicant]
Zhan et al., A New Hyperspectral Band Selection Approach based on Convolutional Neural Network, IEEE International Geoscience mid Remote Sensing Symposium, Jul. 23-28, 2017, pp. 3660-3663. [cited by applicant]
Zhang et al., Cross-Scene Crowd Counting via Deep Convolutional Neural Networks, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Jun. 2015, pp. 833-841. [cited by applicant]
Zhao et al., Chromatic Aberrations Correction for Imaging Spectrometer Based on Acousto-Optic Tunable Filter with Two Transducers, Optics Express, vol. 25, No. 20, Oct. 2, 2017, pp. 23809-23825. [cited by applicant]
Zhao et al., Spectral-Spatial Feature Extraction for Hyperspectral Image Classification: A Dimension Reduction and Deep Learning Approach, IEEE Transactions on Geoscience and Remote Sensing, vol. 54, No. 8, Aug. 2016, p… [cited by applicant]
Zhao et al., Using Deep Learning in Image Hyper Spectral Segmentation, Classification, and Detection, Fourth Seminar on Novel Optoelectronic Detection Technology and Application, vol. 10697, Feb. 20, 2018, 6 pages. [cited by applicant]