Small Aerial Target Detection Using Trajectory Hypothesis and Verification
Small Aerial Target Detection Using Trajectory Hypothesis and Verification
复制标题
DOI：
10.1109/tgrs.2023.3271725
复制
发表时间：
2023
影响因子：
8.2
通讯作者：
Liangchao Guo;Xiaoliang Sun;Wenlong Zhang;Zhang Li;Qifeng Yu
中科院分区：
文献类型：
--
作者：
Liangchao Guo;Xiaoliang Sun;Wenlong Zhang;Zhang Li;Qifeng Yu
由于杂乱的背景、远距离成像、快速相对运动等，空中小目标的检测仍然是一个挑战。现有的工作已经说明了时间线索对于稳健的小型空中目标检测的重要性。然而，对时间线索的强烈假设使得此类方法计算复杂度高，适应性弱。为了解决这个问题，我们将轨迹验证视为使用卷积神经网络的分类问题。本研究提出了一种利用轨迹假设和验证的新型小型空中目标检测方法。首先，使用惯性测量单元（IMU）辅助的帧间差异从每个单图像中提取目标候选者。然后，基于目标轨迹的连续性和平滑性特征，通过链接相邻帧中的目标候选来生成所需长度的假设。最后，轨迹假设被发送到经过训练的分类卷积神经网络进行验证。检测到的目标是从验证的轨迹追溯到的。此外，进行轨迹合并以链接相邻的轨迹段。所提出的方法可以实现实时处理。在公共数据集上的实验结果表明，所提出的方法比现有方法表现更好。
Due to cluttered backgrounds, long-range imaging, rapid relative motion, etc., the detection of small aerial targets remains a challenge. Existing works have illustrated the importance of temporal cues for robust small aerial target detection. However, the strong assumptions about the temporal cues give such methods high-computational complexity and weak adaptability. To address this problem, we treat trajectory verification as a classification problem using convolutional neural networks. A novel small aerial target detection method that uses trajectory hypothesis and verification is proposed in this study. First, the inertial measurement unit (IMU)-assisted interframe difference is used to extract target candidates from each single image. Then, based on the continuous and smoothness characteristics of the target trajectory, hypotheses of the required length are generated by linking target candidates in adjacent frames. Finally, the trajectory hypotheses are sent to a trained classification convolution neural network for verification. The detected targets are traced back from the verified trajectory. Furthermore, trajectory merge is conducted to link adjacent trajectory segments. The proposed method can achieve real-time processing. Experimental results on public datasets show that the proposed method performs better than existing methods.