Pedestrian detection method based on improved Faster RCNN

Abstract

The invention discloses a pedestrian detection method based on an improved Faster RCNN, and the method comprises the steps: extracting a feature map of a sample image through a ResNet-50 neural network, inputting the obtained feature map into an RPN model, modifying a frame regression loss function of the RPN model, and generating a candidate frame; and finally, sending the feature map and the candidate frame to an ROI Head model to obtain the category and location of the target. The method is based on CNN features, can process images of any scale, and is high in detection precision. Compared with the disclosed invention patent, the method disclosed by the invention does not need to carry out special design on the network, only needs to modify the frame regression loss function of the RPN model, fully utilizes the existing available data, still can achieve a good experiment effect by adopting a universal network structure, fully plays the advantages of the deep convolutional network, and has the advantages of being high in practicability and the like. The method has the advantages of being simple in design, good in robustness, high in detection accuracy and low in omission ratio.

Description

technical field [0001] The invention belongs to the technical field of image processing and computer vision, and relates to a pedestrian detection method based on an improved Faster RCNN. Background technique [0002] Object detection is one of the most important computer vision tasks, dealing with the detection of visual instances of a certain class of objects in cluttered real-world scenes or input images. Due to its wide range of applications, object detection has attracted great attention in recent years. Object detection mainly consists of two tasks: object localization and object classification. Object positioning determines the location and scale of one or more object instances by drawing a bounding box around them. Classification refers to the process of assigning a class label to that object. In terms of detection, object detection systems build models from a set of training data, and in terms of generalization, a large number of training data sets need to be pro...

AI Technical Summary

Problems solved by technology

The Two-Stage target detection algorithm can fully learn the characteristics of the target by obtaining the candidate frame in advance, and its detection accuracy and positioning accuracy are high, but the network structure is complex, the calculation is large, and the detection speed is slow, so it is not suitable for real-time requirements. high application scenarios

The One-Stage target detection algorithm has a simple structure and can directly process the input image. The detection speed is fast and can be applied to real-time detection. However, the One-Stage algorithm has low detection accuracy for small targets and multi-target objects.

Images