Computer vision recognition and tracking algorithm based on convolutional neural network

Abstract

In the past few decades, target tracking algorithm has been paid great attention by peers at home and abroad in the field of computer vision because of its potential for in-depth research and practical value. Typical applications of target tracking algorithms include intelligent video surveillance, autonomous vehicles, human-computer interaction and so on. Given the initial state of a target object, the task of the target tracking algorithm is to estimate the state of the target in the subsequent video. Despite years of efforts, designing a target tracking algorithm is still a very challenging problem, because it poses changes, particularly illumination changes, and in addition, occlusion, complex environments, and the moving background will also cause changes in the appearance of the target. The traditional target tracking algorithm based on manually designed features or shallow classifiers uses manually designed low-level visual features or shallow classifiers to build the target apparent model, so the semantic information prediction ability of the target apparent model is limited. Given the defect that the above traditional target tracking algorithm is difficult to capture the semantic information of visual data in the target apparent model, inspired by the great success of deep convolution networks in image classification and speech recognition, a target tracking algorithm based on convolution neural network is proposed in this paper.

Review of object tracking algorithms in computer vision based on deep learning

“…Convolutional neural network is a layered model that can learn features directly from image original pixels [3]. Firstly, in the first stage, the 32*32 pre-processed black and white image is input into the convolution layer composed of 6 5*5 filters, and the feature map size is 28*28.…”

“…Particle filter is a recursive Bayesian filtering algorithm, which uses sequential Monte Carlo important sampling method to represent the posterior probability. The core idea is to approximate a posterior probability distribution using a series of random particles [3] In the above formula, 𝑝(𝑥 𝑡 𝑥 𝑡−1 ), 𝑝(𝑦 𝑡 𝑥 𝑡 ) are the dynamic model and the observation model, respectively. ssThe optimal target state x at the last time t can be obtained from the maximum posterior probability:…”