Pedestrian detection network, model training method, detection method, medium and equipment

Abstract

The invention discloses a pedestrian detection network, which takes VGG16 as a basic network and comprises five characteristic layers, namely fc6, fc7, conv6 _ 2, conv7 _ 2 and conv8 _ 2. The invention also discloses a pedestrian detection network model training method. The method comprises the following steps: calculating an expected value E of the pedestrian frame width-to-height ratio; extracting features to obtain a confidence map and a coordinate bias map; making a dense frame generation strategy; preprocessing the training data file, and training a pedestrian detection network to obtaina pedestrian detection network model. The invention also discloses a pedestrian detection method, which comprises the following steps of: setting a detection threshold value, loading the pedestrian detection network model and initializing network parameters; sending the picture into a model to obtain a detection result; filtering all the detection frames through non-maximum suppression to remove the frames detected repeatedly, and finally storing the result in a file. The method is based on the dense frame generation network, effectively overcomes the defects of high leak detection rate and the like in a pedestrian dense scene in the prior art, and improves the detection performance of the frame in the pedestrian dense scene.

Description

technical field [0001] The invention relates to the field of deep learning and pedestrian detection, in particular to a dense pedestrian detection network and model training method, a dense pedestrian detection method, medium, and equipment. Background technique [0002] The advent of the big data era has brought about a major transformation of the times. From scientific research to medical insurance, from banking to the Internet, the technology and information technology industry is constantly developing. Especially in recent years, artificial intelligence has begun to enter people's field of vision. Artificial intelligence is a discipline that studies how to use computers to simulate the way of thinking of the human brain and make decisions. Its fields include intelligent robots, computer vision, natural language processing, and expert systems. As an important research field of artificial intelligence, computer vision has always been a research hotspot in academia and ind...

AI Technical Summary

Problems solved by technology

In 2016, Redmon et al. published the paper "You Only Look Once: Unified, Real-Time Object Detection" at the CVPR conference, and proposed the YOLO target detection method. This method uses the idea of ​​regression, given the input image, directly in the multiple Regress the target frame and target category at this position, which greatly improves the speed of target detection, but the detection accuracy is not very good.

However, DPM is a manually designed feature. At present, many methods for dense pedestrian detection are still stuck in the traditional manual feature and the combination of manual feature and convolutional neural network. Compared with the deep learning method, the detection performance is insufficient. However, target detection algorithms such as Faster R-CNN, YOLO, and SSD are directly used for dense detection, and there is also a problem of performance degradation.

The reason is that in the scene where dense pedestrians appear, pedestrians block each other, and there are too many similarities in the characteristics of different pedestrians, which will affect the judgment of the detector

Images