Person search system based on multiple deep learning models
A computer-implemented method executed by at least one processor for person identification is presented. The method includes employing one or more cameras to receive a video stream including a plurality of frames to extract features therefrom, detecting, via an object detection model, objects within the plurality of frames, detecting, via a key point detection model, persons within the plurality of frames, detecting, via a color detection model, color of clothing worn by the persons, detecting, via a gender and age detection model, an age and a gender of the persons, establishing a spatial connection between the objects and the persons, storing the features in a feature database, each feature associated with a confidence value, and normalizing, via a ranking component, the confidence values of each of the features.
1. A computer-implemented method executed by at least one processor for person identification, the method comprising:
employing one or more cameras to receive a video stream including a plurality of frames to extract features therefrom;
detecting, via an object detection model, objects within the plurality of frames;
detecting, via a key point detection model, persons within the plurality of frames;
detecting, via a color detection model, color of clothing worn by the persons;
detecting, via a gender and age detection model, an age and a gender of the persons;
establishing a spatial connection between the objects and the persons;
storing the features in a feature database, each feature associated with a confidence value; and
normalizing, via a ranking component, the confidence values of each of the features,
wherein the features are sorted based on a summed weight.
2. The method of claim 1 , wherein the key point detection model identifies features related to a face region, a top body region, and a bottom body region of the individuals.
3. The method of claim 2 , wherein the gender and age detection model is applied to the face region of the individuals.
4. The method of claim 1 , wherein the object detection model, the key point detection model, the color detection model, and the gender and age detection model are deep learning models.
5. The method of claim 1 , wherein the confidence value is between 0 and 1.
6. The method of claim 1 , wherein a user searches the feature database to manually conduct a person match.
7. The method of claim 6 , wherein the user conducts either a voice-based search or a text-based search for the person match.
8. A system for person identification, the system comprising:
a memory; and
a processor in communication with the memory, wherein the processor runs program code to:
employ one or more cameras to receive a video stream including a plurality of frames to extract features therefrom;
detect, via an object detection model, objects within the plurality of frames;
detect, via a key point detection model, persons within the plurality of frames;
detect, via a color detection model, color of clothing worn by the persons;
detect, via a gender and age detection model, an age and a gender of the persons;
establish a spatial connection between the objects and the persons;
store the features in a feature database, each feature associated with a confidence value; and
normalize, via a ranking component, the confidence values of each of the features,
wherein the features are sorted based on a summed weight.
9. The system of claim 8 , wherein the key point detection model identifies features related to a face region, a top body region, and a bottom body region of the individuals.
10. The system of claim 9 , wherein the gender and age detection model is applied to the face region of the individuals.
11. The system of claim 8 , wherein the object detection model, the key point detection model, the color detection model, and the gender and age detection model are deep learning models.
12. The system of claim 8 , wherein the confidence value is between 0 and 1.
13. The system of claim 8 , wherein a user searches the feature database to manually conduct a person match.
14. The system of claim 13 , wherein the user conducts either a voice-based search or a text-based search for the person match.
15. A non-transitory computer-readable storage medium comprising a computer-readable program for person identification, wherein the computer-readable program when executed on a computer causes the computer to perform the steps of:
employing one or more cameras to receive a video stream including a plurality of frames to extract features therefrom;
detecting, via an object detection model, objects within the plurality of frames;
detecting, via a key point detection model, persons within the plurality of frames;
detecting, via a color detection model, color of clothing worn by the persons;
detecting, via a gender and age detection model, an age and a gender of the persons;
establishing a spatial connection between the objects and the persons;
storing the features in a feature database, each feature associated with a confidence value; and
normalizing, via a ranking component, the confidence values of each of the features,
wherein the features are sorted based on a summed weight.
16. The non-transitory computer-readable storage medium of claim 15 , wherein the object detection model, the key point detection model, the color detection model, and the gender and age detection model are deep learning models.
17. The non-transitory computer-readable storage medium of claim 15 , wherein a user searches the feature database to manually conduct a person match.