A vehicle detection method based on yolo v3 improved algorithm

Abstract

The invention discloses a vehicle detection method based on the YOLO v3 improved algorithm. Including steps: S1. Collect a vehicle data set, the vehicle data set contains multiple images I of the GT frame of the object; S2. Use a dimensional clustering method to cluster the width and height of the GT frame, and generate the width and height of K a priori frames. High size; S3. Input the image I into the skeleton network Darknet‑53 of YOLO v3 for feature extraction, and output feature maps of different scales; S4. Evenly distribute the K a priori frame sizes to the feature maps of different scales. Predict and generate the corresponding candidate frame; S5, select the final prediction frame according to the generated candidate frame; S6, map the final prediction frame to the original image according to the relationship between the feature map and the original image, and locate the vehicle information in the image . This method improves the calculation formula of the distance between the GT frame and the cluster center, reduces the sensitivity of the formula to the IoU value, makes the size of the a priori frame obtained by clustering more in line with the real value, and improves the quality of the prior frame. Improved the performance of the YOLO v3 detection method.

Description

technical field

[0001] The invention belongs to the field of image target detection, in particular to a vehicle detection method based on an improved algorithm of YOLO v3. Background technique

[0002] Object detection is an important building block in the field of computer vision. Among them, vehicle detection is a hot research issue in the field of target detection, and has important applications in assisted driving, road monitoring, and remote sensing images. The goal of vehicle detection is to quickly detect vehicle targets and their related feature information from pictures or videos.

[0003] Traditional machine learning-based vehicle detection usually includes two steps: first, feature extraction is performed, and then based on the extracted feature vectors, it is classified using a classifier. Commonly used feature extraction methods include Local Binary Pattern (LBP), Histogram of Oriented Gradient (HOG), Scale Invariant Feature Transform (SIFT), etc. Commonly us...

Images