A deep learning method based on multi-task and proximity information fusion based on target detection

Abstract

The invention discloses a deep learning method based on multi-task of target detection and fusion of adjacent information, which includes inputting a picture, using a convolutional neural network to extract image features, and generating a target candidate frame; passing the target candidate frame through a region candidate network to extract Extract the target prediction frame; perform feature extraction and feature pooling on the target prediction frame, and then perform frame regression, direction prediction, and target detection classification to obtain preliminary detection results; fuse the preliminary detection results with the target candidate frame and enter the RO I pooling layer And through the second fully connected layer, the final detection result is obtained; among them, the target detection classification is to use the information relationship between a target prediction frame and other adjacent target prediction frames to redefine the confidence score of the target prediction frame; the algorithm adopts multi-task output mode. The invention ensures the accuracy of target detection while improving the speed of target detection, and meets the requirement of real-time target detection.

Description

technical field [0001] The invention relates to the field of image information processing, in particular to a multi-task based target detection and a deep learning method for fusion of adjacent information. Background technique [0002] At present, target detection has always been a basic problem in the application of visual computing, which is applied in traffic monitoring, intelligent driving and other fields. In real conditions, on the one hand, due to the diversity of targets such as vehicles, pedestrians, numbers, railings, etc. on the road, there are many subcategories of targets such as buses, cars, trucks, bicycles, etc. on the other hand. The target has multiple angles, different occlusion situations and the local size of the target display, which brings great difficulty to target detection. Target detection is still a very challenging field, and in order to achieve target detection, recognition, and tracking in real time, there are quite high requirements for dete...

AI Technical Summary

Problems solved by technology

[0003] Starting from RCNN, namely Regions with CNN features, the convolutional neural network was introduced into the field of target detection, which greatly improved the effect of target detection; subsequently, SppNET, Fast-RCNN and Faster-RCNN were proposed to further accelerate the convolutional neural network in target detection. field of application, but at the same time there is a contradiction between accuracy and recognition speed, the recognition speed is reduced due to repeated feature extraction and calculation, and a large storage space is required

In addition, there is also a structure of YOLO, which is You only look once, which has a fast recognition speed, but at the expense of a certain accuracy rate.

Images