Target detection method and apparatus
View Patent ↗A target detection method and apparatus. The method comprises: acquiring an input image, and sending same to a candidate region generation network to generate a plurality of regions of interest; formatting the plurality of regions of interest, and then sending same to a target key point network to generate a thermodynamic diagram; using a global feature map of the input image to perform convolution on the thermodynamic diagram, so as to generate a local depth feature map; and fusing the global feature map and the local depth feature map, and detecting a target therefrom by means of a detector. The present invention can be applied to target detection at different scales, improves the detection accuracy and robustness of a target detection technique for an occluded target in complex scenarios, and achieves, by means of making full use of local key point information of the target, target positioning under occlusion.
1. A target detection method, comprising the following steps:
acquiring an input image, and sending same to a candidate region generation network to generate a plurality of regions of interest;
adjusting the plurality of regions of interest to a same size, and then sending same to a target key point network to generate a heat map;
using a global feature map of the input image to perform convolution on the heat map, so as to generate a local depth feature map wherein the global feature map is generated by a global feature generation network; and
fusing the global feature map and the local depth feature map, and detecting a target therefrom by means of a detector.
2. The method according to claim 1 , wherein the detector comprises a deep convolutional neural network with a full connection layer and a classification layer removed and an additional new convolutional layer arranged.
3. The method according to claim 2 , wherein the new convolutional layer comprises a first new convolutional layer and a second new convolutional layer with different receptive fields and resolutions to detect targets of different scales.
4. A target detection apparatus, comprising:
a processor; and
a memory storing program code runnable by the processor, the program code, when run, performing the following steps:
acquiring an input image, and sending same to a candidate region generation network to generate a plurality of regions of interest;
adjusting the plurality of regions of interest to a same size, and then sending same to a target key point network to generate a heat map;
using a global feature map of the input image to perform convolution on the heat map, so as to generate a local depth feature map wherein the global feature map is generated by a global feature generation network; and
fusing the global feature map and the local depth feature map, and detecting a target therefrom by means of a detector.
5. The apparatus according to claim 4 , wherein the detector comprises a deep convolutional neural network with a full connection layer and a classification layer removed and an additional new convolutional layer arranged.
6. The apparatus according to claim 5 , wherein the new convolutional layer comprises a first new convolutional layer with high resolution and a small receptive field to detect a small target and a second new convolutional layer with low resolution and a large receptive field to detect a large target.