10 February 2022 in Applied Nanoscience
5 July 2023 in Digital Signal Processing
8 August 2022 in Neural Processing Letters
1 January 2021 in Complexity
In this paper, to better solve the problem of low tracking accuracy caused by the sudden change of target scale, we design and propose an adaptive scale mutation tracking algorithm using a deep learning network to detect the target first and then track it using the kernel correlation filtering method and verify the effectiveness of the model through experiments. The improvement point of this paper is to change the traditional kernel correlation filtering algorithm to detect and track at the same time and to combine deep learning with traditional kernel correlation filtering tracking to apply in the process of target tracking; the addition of deep learning network not only can learn more accurate feature representation but also can more effectively cope with the low resolution of video sequences, so that the algorithm in the case of scale mutation achieves more accurate target tracking in the case of scale mutation. To verify the effectiveness of this method in the case of scale mutation, four evaluation criteria, namely, average accuracy, cross‐ratio accuracy, temporal robustness, and spatial robustness, are combined to demonstrate the effectiveness of the algorithm in the case of scale mutation. The experimental results verify that the joint detection strategy plays a good role in correcting the tracking drift caused by the subsequent abrupt change of the target scale and the effectiveness of the adaptive template update strategy. By adaptively changing the number of interval frames of neural network redetection to improve the tracking performance, the tracking speed is improved after the fusion of correlation filtering and neural network, and the combination of both is promoted for better application in target tracking tasks.
6 January 2025 in IEEE Access
Remote sensing object detection faces significant challenges due to the varying resolutions of images and the diverse shapes of objects. In this paper, we introduce an innovative approach to enhance object detection networks in remote sensing images by addressing these issues through a novel two-stage training process. Our key contributions include the development of a combined low-resolution pretraining and high-resolution fine-tuning strategy, which significantly improves the model’s generalization capability across different resolutions.We have designed a Pretrained Detail Enhancement and Restoration (PDER) framework that enhances feature extraction from low-resolution images, thereby boosting the baseline network’s ability to handle blurred and intricate objects. Additionally, we propose an Energy-Efficient Shape Adaptive Convolution (EESA) that integrates a depthwise separable mechanism with shape-adaptive feature maps, enabling efficient capture of complex object edges without substantial computational overhead. Compared to state-of-the-art methods such as YOLOv7, our model achieves an absolute average precision improvement of 2.34% and 2.57% on the DIOR and xView datasets, respectively. Extensive experiments on multiple remote sensing datasets demonstrate our approach’s effectiveness, achieving significant improvements in detection accuracy and computational efficiency, thus highlighting its potential for practical applications.