Multi-task joint training crowd counting network method, system, medium and terminal
A crowd counting and multi-tasking technology, applied in the field of crowd recognition, can solve problems such as inability to encode deeper features, and achieve the effects of avoiding image distortion, avoiding crowding, and suppressing negative responses
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0048] This embodiment provides a crowd counting network method for multi-task joint training, the crowd counting network method for multi-task joint training includes:
[0049] Inputting the preprocessed training set to the pre-trained crowd discovery sub-network to predict the crowd image data and background image data in the training set to obtain network prediction categories;
[0050] Carry out the first difference calculation between the network prediction category and the real image category of the training set, and generate an attention feature map through the differentiated crowd image data and background image data; the attention feature map is used to represent the crowd a weight map of the weight values of the image data; meanwhile,
[0051] Input the preprocessed training set to the pre-trained feature extraction sub-network to obtain the spatial feature map;
[0052] performing feature processing on the spatial feature map and the attention feature map, and pe...
Embodiment 2
[0124] This embodiment provides a multi-task joint training crowd counting network system, the multi-task joint training crowd counting network system includes:
[0125] Category prediction module, for inputting the preprocessed training set to the pre-trained crowd discovery sub-network, to predict the crowd image data and background image data in the training set, and obtain the network prediction category;
[0126] The first difference calculation module is used to calculate the first difference between the network prediction category and the image real category of the training set, and generate an attention feature map through the differentiated crowd image data and background image data; the attention The force feature map is a weight map for representing weight values of crowd image data; meanwhile,
[0127] The spatial feature module is used to input the preprocessed training set to the pre-trained feature extraction sub-network to obtain the spatial feature map;
[...
Embodiment 3
[0148] This embodiment provides a terminal, including: a processor, a memory, a transceiver, a communication interface or / and a system bus; the memory and the communication interface are connected to the processor and the transceiver through the system bus to complete mutual communication, and the memory is used for The computer program is stored, the communication interface is used to communicate with other devices, the processor and the transceiver are used to run the computer program, so that the terminal executes various steps of the crowd counting network method for multi-task joint training as described in Embodiment 1.
[0149] The system bus mentioned above may be a Peripheral Component Interconnect (PCI for short) bus or an Extended Industry Standard Architecture (EISA for short) bus or the like. The system bus can be divided into address bus, data bus, control bus and so on. The communication interface is used to realize the communication between the database access ...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More