A long-term tracking method based on the weighted online sample updating is proposed to address the problem of tracking failure caused by target loss during long-term tracking. First, the ResNet50 network is used to extract the deep features of the target and enhance the initial frame sample to optimize the target model, which could improve the influence of the initial frame sample weight. Then, the target model is used to classify the test frame sample, and the confidence score is used to weight the online learning samples to enhance their quality and improve the classification performance of the model. Secondly, the target state is determined by the confidence score, and the target is tracked and located. When the target is lost, a spatiotemporal constraint search is used to adaptively expand the search area at the loss point and randomly search for the target, while utilizing online learning to quickly optimize the target model and enhance its search ability. Finally, an adaptive threshold discrimination method is proposed for the search process, fully utilizing the image background information, using the background confidence score when the target is lost as the discrimination threshold, reducing the influence of similar backgrounds in the search process to accurately retrieve the target. Experiments on the LTB50 dataset show a success rate of 66. 1% and a tracking F-score of 64. 4% , outperforming other methods. Real-world experiments on a quadruped robot platform achieved success rates of 87. 8% and 85. 8% under full occlusion and out-of-view scenarios, respectively. The effectiveness of the proposed method is evaluated.