MOTION-BASED OBJECT DETECTION METHOD, OBJECT DETECTION APPARATUS AND ELECTRONIC DEVICE

1 . A motion-based object detection method, comprising:

extracting, by processing acquired first and second images, one or more regions of interest (ROIs);

transforming the one or more ROIs into grayscale; and

acquiring, by processing the grayscale ROIs with a deep neural network (DNN) model to classify objects contained in the one or more ROIs, a classification result of whether the objects contained in the one or more ROIs belong to a given categories, wherein the DNN model comprises N depthwise separable convolution layers, wherein each depthwise separable convolution layer comprises a depthwise convolution layer for applying a single filter to each input channel and a pointwise layer for linearly combining outputs of the depthwise convolution layer to obtain feature maps of the grayscale ROIs, wherein N is a positive integer and ranged from 4-12.

2 . The motion-based object detection method, as recited in claim 1 , wherein the step of acquiring a classification result further comprises the steps of:

determining whether any one of the objects contained in the one or more ROIs belong to the given categories; and

generating, responsive to the determination, an indication of a presence of the objects contained in the one or more ROIs belonging to the given categories.

3 . The motion-based object detection method, as recited in claim 2 , wherein the step of extracting the one or more ROIs, comprises the steps of:

identifying different image regions between the first image and the second image; and

grouping the different image regions between the first image and the second image into the one or more ROIs.

4 . The motion-based object detection method, as recited in claim 3 , wherein prior to the step of identifying the different image regions between the first image and the second image, the method further comprising the step of:

transforming the second image to compensate for physical movement of an image collecting apparatus when capturing the first image and the second image.

5 . The motion-based object detection method, as recited in claim 4 , wherein the first and second images are two consecutive frames of a video.

6 . The motion-based object detection method, as recited in claim 5 , wherein the one or more ROIs are scaled to size 128*128 pixels.

7 . The motion-based object detection method, as recited in claim 6 , wherein the DNN model comprise five depthwise separable convolution layers.

8 . An object detection apparatus, comprising:

a region of interest (ROI) extractor configured to extract, by processing acquired first and second images, one or more ROIs;

a grayscale transformer configured to transform the one or more ROIs into grayscale; and

a classification result acquirer configured to acquire, by processing the grayscale ROIs with a deep neural network (DNN) model to classify objects contained in the one or more ROIs, a classification result of whether the objects contained in the one or more ROIs belong to a given categories, wherein the DNN model comprises N depthwise separable convolution layers, wherein each depthwise separable convolution layer comprises a depthwise convolution layer for applying a single filter to each input channel and a pointwise layer for linearly combining outputs of the depthwise convolution layer to obtain feature maps of the grayscale ROIs, wherein N is a positive integer and ranged from 4-12.

9 . The object detection apparatus, as recited in claim 8 , wherein the classification result acquirer is further configured to:

determine whether any one of the objects contained in the one or more ROIs belong to the given categories; and

generate, responsive to the determination, an indication of a presence of the objects contained in the one or more ROIs belonging to the given categories.

10 . The object detection apparatus, as recited in claim 9 , wherein the region of interest extractor is further configured to:

identify different image regions between the first image and the second image; and

group the different image regions between the first image and the second image into the one or more ROIs.

11 . The object detection apparatus, as recited in claim 10 , wherein the region of interest extractor is further configured to:

transform the second image to compensate for physical movement of an image collecting apparatus when capturing the first image and the second image.

12 . The object detection apparatus, as recited in claim 11 , wherein the first and second images are two consecutive frames of a video.

13 . The object detection apparatus, as recited in claim 12 , wherein the one or more ROIs are scaled to size 128*128 pixels.

14 . The object detection apparatus, as recited in claim 13 , wherein the DNN model comprises five depthwise separable convolution layers.

15 . (canceled)

16 . A non-transitory computer storage medium that, when executed by a processor, causes the processor to perform the following method:

processing acquired first and second images, one or more ROIs;

transforming the one or more ROIs into grayscale; and

acquiring, by processing the grayscale ROIs with a deep neural network (DNN) model to classify objects contained in the one or more ROIs, a classification result of whether the objects contained in the one or more ROIs belong to a given categories, wherein the DNN model comprises N depthwise separable convolution layers, wherein each depthwise separable convolution layer comprises a depthwise convolution layer for applying a single filter to each input channel and a pointwise layer for linearly combining outputs of the depthwise convolution layer to obtain feature maps of the grayscale ROIs, wherein N is a positive integer and ranged from 4-12.