In order to solve the problem of detecting, tracking and estimating the size of “low, slow and small” targets (such as UAVs) in the air, this paper designs a single-photon LiDAR imaging system based on Geiger-mode Avalanche Photodiode (Gm-APD). It improves the Mean-Shift algorithm and proposes an automatic tracking method that combines the weighted centroid method to realize target extraction, and the principal component analysis (PCA) method of the adaptive rotating rectangle is realized to fit the flight attitude of the target. This method uses the target intensity and distance information provided by Gm-APD LiDAR. It addresses the problem of automatic calibration and size estimation under multiple flight attitudes. The experimental results show that the improved algorithm can automatically track the targets in different flight attitudes in real time and accurately calculate their sizes. The improved algorithm is stable in the 1250-frame tracking experiment of DJI Elf 4 UAV with a flying speed of 5 m/s and a flying distance of 100 m. Among them, the fitting error of the target is always less than 2 pixels, while the size calculation error of the target is less than 2.5 cm. This shows the remarkable advantages of Gm-APD LiDAR in detecting “low, slow and small” targets. It is of practical significance to comprehensively improve the ability of UAV detection and C-UAS systems. However, the application of this technology in complex backgrounds, especially in occlusion or multi-target tracking, still faces certain challenges. In order to realize long-distance detection, further optimizing the field of view of the Gm-APD single-photon LiDAR is still a future research direction.

With the wide application of UAVs in modern intelligent warfare as well as in civil fields, the demand for C-UAS technology is increasingly urgent. Traditional detection methods have many limitations in dealing with “low, slow, and small” targets. This paper presents a pure laser automatic tracking system based on Geiger-mode avalanche photodiode (Gm-APD). Combining the target motion state prediction of the Kalman filter and the adaptive target tracking of Camshift, a Cam–Kalm algorithm is proposed to achieve high-precision and stable tracking of moving targets. The proposed system also introduces two-dimensional Gaussian fitting and edge detection algorithms to automatically determine the target’s center position and the tracking rectangular box, thereby improving the automation of target tracking. Experimental results show that the system designed in this paper can effectively track UAVs in a 70 m laboratory environment and a 3.07 km to 3.32 km long-distance scene while achieving low center positioning error and MSE. This technology provides a new solution for real-time tracking and ranging of long-distance UAVs, shows the potential of pure laser approaches in long-distancelow, slow, and small target tracking, and provides essential technical support for C-UAS technology.

Geiger-mode avalanche photodiode (GM-APD) is a single-photon-detection device characterized by high sensitivity and fast response, which enables it to detect echo signals of distant targets effectively. Given that weak and small targets possess relatively small volumes and occupy only a small number of pixels, relying solely on neighborhood information for target reconstruction proves to be difficult. Furthermore, during long-distance detection, the optical reflection cross-section is small, making signal photons highly susceptible to being submerged by noise. In this paper, a noise fitting and removal algorithm (NFRA) is proposed. This algorithm can detect the position of the echo signal from the photon statistical histogram submerged by noise and facilitate the reconstruction of weak and small targets. To evaluate the NFRA method, this paper establishes an optical detection system for remotely detecting active single-photon weak and small targets based on GM-APD. Taking unmanned aerial vehicles (UAVs) as weak and small targets for detection, this paper compares the target reconstruction effects of the peak-value method and the neighborhood method. It is thereby verified that under the conditions of a 7 km distance and a signal-to-background ratio (SBR) of 0.0044, the NFRA method can effectively detect the weak echo signal of the UAV.

The photon-counting light laser detection and ranging (LiDAR), especially the Geiger mode avalanche photon diode (Gm-APD) LiDAR, can obtain three-dimensional images of the scene, with the characteristics of single-photon sensitivity, but the background noise limits the imaging quality of the laser radar. In order to solve this problem, a depth image estimation method based on a two-dimensional (2D) Kaniadakis entropy thresholding method is proposed which transforms a weak signal extraction problem into a denoising problem for point cloud data. The characteristics of signal peak aggregation in the data and the spatio-temporal correlation features between target image elements in the point cloud-intensity data are exploited. Through adequate simulations and outdoor target-imaging experiments under different signal-to-background ratios (SBRs), the effectiveness of the method under low signal-to-background ratio conditions is demonstrated. When the SBR is 0.025, the proposed method reaches a target recovery rate of 91.7%, which is better than the existing typical methods, such as the Peak-picking method, Cross-Correlation method, and the sparse Poisson intensity reconstruction algorithm (SPIRAL), which achieve a target recovery rate of 15.7%, 7.0%, and 18.4%, respectively. Additionally, comparing with the SPIRAL, the reconstruction recovery ratio is improved by 73.3%. The proposed method greatly improves the integrity of the target under high-background-noise environments and finally provides a basis for feature extraction and target recognition.

This study proposes a complete data-processing framework for Geiger-mode avalanche photodiode (GM-APD) light detection and ranging (LiDAR) echo signals. It investigates the feasibility of classifying target and background noise using machine learning. Four feature processing schemes were first compared, among which the PNT strategy (Principal Component Analysis without tail features) was identified as the most effective and adopted for subsequent analysis. Based on this framework, nine models derived from six baseline algorithms—Decision Trees (DTs), Support Vector Machines (SVMs), Backpropagation Neural Networks (NN-BPs), Linear Discriminant Analysis (LDA), Logistic Regression (LR), and k-Nearest Neighbors (KNN)—were systematically assessed under Monte Carlo simulations with varying echo signal-to-noise ratio (ESNR) and statistical frame number (SFN) conditions. Model performance was evaluated using eight metrics: accuracy, precision, recall, FPR, FNR, F1-score, Kappa coefficient, and relative change percentage (RCP). Monte Carlo simulations were employed to generate datasets, and Principal Component Analysis (PCA) was applied for feature extraction in the machine learning training process. The results show that LDA achieves the shortest training time (0.38 s at SFN = 20,000), DT maintains stable accuracy (0.7171–0.8247) across different SFNs, and NN-BP models perform optimally under low-SNR conditions. Specifically, NN-BP-3 achieves the highest test accuracy of 0.9213 at SFN = 20,000, while NN-BP-2 records the highest training accuracy of 0.9137. Regarding stability, NN-BP-3 exhibits the smallest RCP value (0.0111), whereas SVM-3 yields the largest (0.1937) at the same frame count. In conclusion, NN-BP-based models demonstrate clear advantages in classifying sky-background noise. Building on this, we design a ResNet based on NN-BP, which achieves further accuracy gains over the best baseline at 400, 2000, and 20,000 frames—12.5% (400), 9.16% (2000), and 2.79% (20,000)—clearly demonstrating the advantage of NN-BP for GM-APD LiDAR signal classification. This research thus establishes a novel framework for GM-APD LiDAR signal classification, provides the first systematic comparison of multiple machine learning models, and highlights the trade-off between accuracy and computational efficiency. The findings confirm the feasibility of applying machine learning to GM-APD data and offer practical guidance for balancing detection performance with real-time requirements in field applications.