Vehicle-mounted video target detection method based on deep learning

Abstract

The invention discloses a vehicle-mounted video target detection method based on deep learning, and the method comprises the steps: employing an improved Faster R-CNN algorithm to realize target detection in a complex traffic environment, to provide a driving safety auxiliary function. An existing target tracking algorithm has a serious problem of small target missed detection. The depth information channel is added, the depth information channel is connected with an original color image channel in parallel, fusion is carried out in the channel dimension, candidate frame extraction and targetdetection are carried out on the fused feature image, the detection rate of a small target is improved, in addition, training of a difficult sample is added in training, and the overall target recognition rate of the algorithm is improved. According to the method, a problem of small target missed detection by using the Faster R-CNN algorithm is fully considered. The accuracy of vehicle recognitionin a complex traffic scene is improved through depth image feature fusion and a difficult sample mining method.

Description

technical field [0001] The invention relates to a vehicle-mounted video target detection method based on deep learning, and belongs to the technical field of video image processing. Background technique [0002] In the process of driving, it is the basis of the driving safety assistance system to detect and track the vehicles, pedestrians and other obstacles in front of the vehicle, and to analyze the behavior of the vehicle in front on this basis. The main steps of traditional target detection methods are generally: extracting target features, training corresponding classifiers, sliding window search, repetition and false positive filtering. This kind of sliding window selection strategy for target detection is not targeted, has high time complexity, redundant windows, and the hand-designed features are less robust, and the classifier is not reliable; at the same time, the existing target detection algorithms cannot be trained flexibly. The data can be used to learn effect...

AI Technical Summary

Problems solved by technology

This kind of sliding window selection strategy for target detection is not targeted, has high time complexity, redundant windows, and the hand-designed features are less robust, and the classifier is not reliable; at the same time, the existing target detection algorithms cannot be trained flexibly. Data to learn effective features according to different needs to complete specific detection tasks

Images