Target tracking algorithm based on dense connection convolutional neural network

Abstract

The invention discloses a target tracking algorithm based on a dense connection convolutional neural network, and the algorithm comprises the following steps of S101, extracting the characteristics ofan input image, employing the dense connection convolutional neural network as a characteristic extraction network in advance, and obtaining the characteristics of an extracted output image; S103, carrying out output feature map processing, performing bilinear interpolation on the obtained extracted output image features to obtain a bilinear interpolation feature map; and S105, calculating to obtain the feature map. The algorithm has the beneficial effects that the densely connected convolutional neural network is used for replacing a feature extraction network of a traditional twin convolutional network, so that the network obtains the higher feature extraction capability; the bilinear interpolation is carried out on a feature graph outputteed by a feature extraction network, so that theresolution of the feature graph is improved, the positioning precision of a tracking algorithm is improved; and in addition, an RPN layer is added on the basis of a traditional twinning convolutionalnetwork, so that the distinguishing capability of the tracking algorithm on a target and a background is enhanced.

Description

technical field [0001] The invention relates to the technical fields of deep learning and computer vision, in particular to a target tracking algorithm based on a densely connected convolutional neural network. Background technique [0002] Object tracking technology is an important branch of computer vision tasks and is widely used in areas such as autonomous driving, video surveillance, and robotics. Traditional target tracking algorithms mainly rely on manual labeling features and related filtering algorithms (such as KCF, TLD, etc.), which have a high frame rate, but low accuracy and robustness, which are difficult to meet the requirements of practical applications. In recent years, with the rise of artificial intelligence and deep learning, the convolutional neural network algorithm has gradually entered the field of target tracking, and has achieved good performance and results. Among them, the algorithm framework based on the twin convolutional network relies on its g...

AI Technical Summary

Problems solved by technology

The feature map obtained through the feature extraction network usually has higher-level semantic information, but the resolution is small, and the original position information of the image is seriously lost, which affects the accuracy of target positioning.

Images