Improved target detection method based on residual network

Abstract

The invention discloses an improved target detection method based on a residual network, based on YOLO V3-tiny network, features are extracted through continuous convolution operation, finally, pictures are divided into 13*13 grids, for each grid unit, a detection frame of a target with a center point falling into the grid unit is predicted through three anchor frames. The method specifically comprises the following steps of determining the number of types of the target to be identified to form a data set; establishing a target detection neural network; obtaining training weight files. Throughthe lightweight target detection network YOLOV3-tiny, the calculation amount is small, the target detection task can be carried out in the embedded hardware, and the real-time performance is ensured.According to the method, the original feature extraction network is replaced by the residual network resnet18, and for the feature extraction network with the same layer number, the feature extraction capability of the network can be improved by adding the residual structure by the residual network, so that the target detection precision can be improved on the premise that the detection speed isnot reduced.

Description

technical field [0001] The invention belongs to the technical field of image recognition, and in particular relates to an optimization method based on a target detection neural network YOLOV3-tiny algorithm, which is particularly suitable for performing target detection tasks on hardware with weak computing capabilities such as embedded platforms. Background technique [0002] In recent years, with the development of artificial intelligence and deep learning technology, the use of convolutional neural networks for image understanding tasks has gradually replaced the method of manually extracting features to make classifiers. For the convolutional neural network model, as the number of network layers increases, the neural network understands images more and more, and the accuracy of target detection and recognition becomes higher and higher, but the amount of calculation also increases. Currently, target detection algorithms are generally computed on servers with GPU accelera...

AI Technical Summary

Problems solved by technology

The feature extraction layer of YOLOV3-tiny consists of seven convolutional layers and 6 pooling layers. The parameters of each layer are shown in Table 1. Although YOLOV3-tiny is a target detection network that can run on low-performance hardware, but Its feature extraction ability is weak, and it often cannot get good detection results.

Images