Due to the limitations of small targets in remote sensing images, such as background noise, poor information, and so on, the results of commonly used detection algorithms in small target detection is not satisfactory. To improve the accuracy of detection results, we develop an improved algorithm based on YOLOv8, called LAR-YOLOv8. First, in the feature extraction network, the local module is enhanced by using the dual-branch architecture attention mechanism, while the vision transformer block is used to maximize the representation of the feature map. Second, an attention-guided bidirectional feature pyramid network is designed to generate more discriminative information by efficiently extracting feature from the shallow network through a dynamic sparse attention mechanism, and adding top–down paths to guide the subsequent network modules for feature fusion. Finally, the RIOU loss function is proposed to avoid the failure of the loss function and improve the shape consistency between the predicted and ground-truth box. Experimental results on NWPU VHR-10, RSOD, and CARPK datasets verify that LAR-YOLOv8 achieves satisfactory results in terms of mAP (small), mAP, model parameters, and FPS, and can prove that our modifications made to the original YOLOv8 model are effective.

To explore lidar, which can simultaneously measure the distance and velocity of long-distance targets at high resolution, a coherent lidar system based on chirp pulse compression has been studied. Instead of a conventional acousto-optic modulator (AOM), we used an electro-optic modulator (EOM) to modulate a continuous 1550 nm laser. Using EOM, the resolution of the lidar is higher and the system simpler. The electrical waveform used to modulate the laser is a chirp pulse, which has a sweeping bandwidth of 98 MHz, a duration of 10 µs, and a pulse repetition rate of 20 kHz. The result of 100 measurements shows that the system may yield accurate information in range, ±22 cm, and radial velocity, ±1.066 cm/s.

In order to eliminate the influence of laser frequency nonlinearity, the frequency-scanning interferometry (FSI) often uses the beat signal of an auxiliary interferometer as the external clock. The time points at every amplitude peaks and bottoms of the auxiliary beat signal are selected as the sampling time points for the main interferometer signal. To satisfy the Nyquist sampling requirement, the optical path difference (OPD) of the delay fiber in auxiliary interferometer should be at least twice longer than the measurement distance. In this paper, we proposed a method to shorten the length of delay fiber. The Hilbert transform was used to extract the phase of the auxiliary interference signal and calculate the time points corresponding to subdivided phase intervals. Then, the main interference signal was resampled at these moments, and the fast Fourier transform was performed on the resampled signal. The experimental results showed that the target at the distance of about 5 m was measured when the OPD of the auxiliary interferometer was about 4.5 m. The standard deviation of the distance measurement results could reach 4.64 μm.

Recent advances in the fields of driverless cars, intelligent robots and remote-sensing measurement have shown that the use of LiDAR fused with cameras can provide more comprehensive and reliable sensing of surroundings. However, since it is difficult to extract features from sparse LiDAR data to create 3D–2D correspondences, finding a method for accurate external calibration of all types of LiDAR with cameras has become a research hotspot. To solve this problem, this paper proposes a method to directly obtain the 3D–2D correspondences of LiDAR–camera systems to complete accurate calibration. In this method, a laser detector card is used as an auxiliary tool to directly obtain the correspondences between laser spots and image pixels, thus solving the problem of difficulty in extracting features from sparse LiDAR data. In addition, a two-stage framework from coarse to fine is designed in this paper, which not only can solve the perspective-n-point problem with observation errors, but also requires only four LiDAR data points and the corresponding pixel information for more accurate external calibration. Finally, extensive simulations and experimental results show that the effectiveness and accuracy of our method are better than existing methods.

A coherent pulse-compression lidar system based on a 90-degree optical hybrid is demonstrated in this paper. In amplitude modulation (AM) mode, the returned RF chirp signal will be influenced by a random phase difference between local oscillator and echo light, causing fluctuations in the ranging results, and as a result the detection probability is small. By using the 90-degree optical hybrid, two orthogonal complementary signals are obtained to stabilize the result so as to increase the detection probability. We performed an experiment to measure the distance of a white printed wall which is about 65 m away from the system. The detection probability increased from 65% to 99.88%, and the precision is improved from 0.42 m to 0.27 m.