Laser through-window imaging technology, an advanced detection method, can effectively penetrate window glass and visualize indoor targets behind the window, providing many application prospects. In antiterrorism and stability maintenance scenarios, a through-window scope enables the capture of accurate information regarding the number and posture of terrorists outside the window. In traffic monitoring applications, this technology enables the assessment of a driver’s status without requiring the driver to exit the vehicle, thereby improving traffic management efficiency. However, the practical application of laser through-window imaging technology faces several challenges. Image quality and accurate capture of target information behind windows are significantly affected by factors such as natural illumination, object occlusion, and strong reflections from the window glass. Accurately detecting human targets and identifying their poses in complex environments is highly challenging. Conventional image processing techniques often cannot achieve accurate and efficient detection results when faced with disruptions such as changes in illumination or occlusion. Addressing these challenges requires the development of more robust object detection and attitude recognition algorithms that can be effectively implemented on edge computing platforms to meet real-time requirements. This study is highly significant, with the potential to substantially enhance fields such as antiterrorism measures, security operations, military reconnaissance activities, and traffic management.

Currently, laser through-window imaging data are not publicly accessible. Therefore, a new dataset was constructed using a laser range-gating imaging system that covers two types of scenes: natural and man-made. The natural scene includes various simulated human postures for data collection, whereas the man-made scene incorporates diverse types of glass, through-window distances, lighting conditions, and occlusions to enhance data diversity. Existing algorithms for human postural recognition in low-quality laser through-window images typically exhibit suboptimal accuracy, which is characterized by significant missed and false detection. Thus, this study used YOLOv8n-Pose as the base model with a targeted optimization design to address these problems. A novel convolution module was developed to improve the feature extraction ability in low-quality image scenarios with laser through-windows, while cross-level association and a model pruning method were used to reconstruct the feature fusion network. This approach aims to reduce the model size and improve the recognition of small target human poses. Additionally, an enhanced detection integration network that combined image denoising and postural recognition tasks enabled end-to-end integrated training, further enhancing the model detection performance. Finally, a human posture recognition algorithm was implemented by deploying the model on the Jetson NX mobile development platform, creating a fully functional airborne laser through-window imaging human posture recognition system.

This study compared the performance of Faster R-CNN, Alphapose, Openpose, HigherHRNet, YOLOv5s6-pose, and YOLOv8n-Pose algorithms for human pose recognition (Table 2). The results indicate that the YOLOv8n-Pose model outperforms Faster R-CNN, Openpose, and HigherHRNet. Alphapose and YOLOv5s6-pose exhibit slightly better performance indicators than YOLOv8n-Pose. However, they significantly lag behind YOLOv8n-Pose in terms of inference speed and model size. Nevertheless, the proposed YOLO-TCpose algorithm performs exceptionally well across various performance indicators. Additional experiments were conducted using the Openpose, Alphapose, and YOLOv8n-Pose algorithms in artificial and natural scenes to assess the effectiveness of the YOLO-TCpose algorithm. In artificial scenes (Fig. 6), comparative experiments involving single and multiple people with occlusion demonstrate that YOLO-TCpose outperforms Openpose and Alphapose by achieving accurate key point positioning and significantly reducing missed detections during multiperson pose recognition. Notably, YOLO-TCpose exhibits significant advantages, particularly in scenarios involving multiperson occlusion. In natural scenes (Fig. 7), the experimental results indicate that during posture recognition tasks such as crawling during the day, standing at night, or squatting on rainy day; YOLO-TCpose accurately detects human target along with their corresponding key points, outperforming other algorithms by a significant margin. Finally, YOLO-TCpose exhibits superior detection accuracy, stability, and adaptability in various environments compared to current mainstream algorithms.

This study introduces YOLO-TCpose, an efficient and lightweight human posture recognition algorithm designed for detecting human poses in low-quality laser through-window images. To address the limitations of traditional convolution, a novel convolutional module was developed to improve feature extraction capabilities. Additionally, the feature fusion network was restructured by eliminating large target detection layers and incorporating small target detection layers. This adjustment facilitates the effective fusion of shallow and deep information through cross-layer connections, thereby improving the recognition performance for small targets. By incorporating an improved ADNet denoising algorithm, an integrated network for image enhancement and pose recognition was developed, which significantly improves the detection accuracy. The experimental results demonstrate that YOLO-TCpose achieves improvements of 19.3 and 26.6 percentage points in the precision and recall rate, respectively, for object detection. The mean average precision (mAP) at 0.5 and mAP at 0.5:0.95 for keypoint detection are enhanced by 16.0 and 10.1 percentage points, respectively. In addition, the inference speed is increased by 5.1 ms, and the model size is reduced by 1.69 MB. Furthermore, algorithms for recognizing three postures—standing, squatting, and crawling—were developed, and the model was successfully deployed on the Jetson NX mobile development platform, establishing a fully functional airborne laser through-window imaging human posture recognition system.