Detection of Weak and Small Targets in Forward-Looking Sonar Image Using Multi-Branch Shuttle Neural Network

In recent years, small and weak target detection technology is one of the hotspots in information processing technology. However, the detection precision and speed of weak targets still have yet to be improved. <br/> As a branch of machine learning, deep learning has become more and more widely used in various fields. Therefore, this paper improves the deep convolutional networks for the characteristics of weak target detection, including the following three aspects: <br/> Firstly, a dataset dedicated to small and weak target detection is established. The data is sufficient and representative, which is beneficial to improve the quality of the network model. Each image in the dataset has a corresponding label that indicates the name of the image, and the coordinates and width of the target circumscribed rectangle. <br/> Secondly, the image is dilated many times so that the target having only a few pixels is covered by a lot of pixels. The highlighted portion of the image is dilated, and the result image has a larger highlighted area than the original image. <br/> Thirdly, the Faster R CNN algorithm is improved. In this paper, by adjusting the learning rates, a suitable one is determined to get the best network model. <br/> The results show that the average precision on the dataset has improved. The method proposed in this paper is of great significance for the detection of small and weak targets. For the military field, the research on weak target detection has high military value for improving early warning capability and counterattack capability.

A fundamental task of radar is the detection of targets in noise and clutter. It is very difficult to detect weak targets in heavy sea clutter. In this paper we apply the discrete wavelet transform (WT), along with multilayer feedforward neural networks, to the detection of radar weak targets. The wavelet transform employs the Haar scaling function, which is well matched to the signals from targets. The hard threshold filter is adopted to remove sea clutter. The neural networks are trained with the back-propagation rule, which are used to detect weak targets. The simulated results show that the proposed method is very effective for radar detection of weak targets.

Infrared small weak target is difficult to detect since it often take up one or two pixel(s) in image. Nonsubsampled contourlet transform based detection algorithms work well in this case, but suffer from expensive time cost. In this paper, a novel infrared weak small target detection algorithm using optimized nonsubsampled contourlet transform is presented. We adopt an optimized nonsubsampled contourlet transform in which marking feature is faster than the original transform. First, raw images are decomposed into low frequency and high frequency coefficients by the optimized nonsubsampled contourlet, then the adaptive mean filter and the Gabor wavelet are used to suppress the background information respectively, in order to eliminate a small quantity of high light points from background, region entropy is used to distinguish background points, considering as false target alarms if not detected and true targets. Experimental results demonstrate that the presented algorithm can detect the infrared weak small targets effectively.

Small and dim target detection is a critical challenge in hyperspectral remote sensing, particularly in complex, large-scale scenes where spectral variability across diverse land cover types complicates the detection process. In this paper, we propose a novel target reasoning algorithm named Adaptive Global Dense Nested Reasoning Network (AGDNR). This algorithm integrates spatial, spectral, and domain knowledge to enhance the detection accuracy of small and dim targets in large-scale environments and simultaneously enables reasoning about target categories. The proposed method involves three key innovations. Firstly, we develop a high-dimensional, multi-layer nested U-Net that facilitates cross-layer feature transfer, preserving high-level features of small and dim targets throughout the network. Secondly, we present a novel approach for computing physicochemical parameters, which enhances the spectral characteristics of targets while minimizing environmental interference. Thirdly, we construct a geographic knowledge graph that incorporates both target and environmental information, enabling global target reasoning and more effective detection of small targets across large-scale scenes. Experimental results on three challenging datasets show that our method outperforms state-of-the-art approaches in detection accuracy and achieves successful classification of different small targets. Consequently, the proposed method offers a robust solution for the precise detection of hyperspectral small targets in large-scale scenarios.

In order to improve the practicability of stochastic resonance (SR) theory in the field of underwater target weak signal detection, taking the parameters of stochastic resonance system as the research object, a signal detection method based on multi feature fusion measure based on particle swarm optimization algorithm is proposed. In this method, the multi-feature fusion measure is taken as the fitness function, and the stochastic resonance problem is transformed into a multi parameter parallel optimization problem. To prove the effectiveness of the above method, we did a set of computer simulation experiments. This method can realize the signal detection of underwater weak and small targets in long-distance low SNR marine environment without relying on a priori information, further improve the signal detection probability, and improve the effectiveness and reliability of underwater weak and small target detection.

Long-term signal accumulation is an effective method to improve the detection of weak and slow small targets. However, the accumulation time is long, and the target echoes will move away from the unit and the Doppler unit, and the coherent accumulation is difficult. In this paper, the small target detection problem based on LTE signal is studied, and the target scattering variability is introduced. The system echo model based on LTE communication system is established. On this basis, the target echo distance walking and Doppler walking characteristics are analyzed. The echo coherent accumulation technique based on keystone transform and fractional Fourier transform (FRFT) is used. Based on the typical target scattering model, the influence of the target scattering characteristics on the accumulation effect is analyzed, and the simulation experiment is carried out under typical system conditions. The validity of the proposed algorithm and analysis is verified.

Sonar image object detection plays a crucial role in obstacle detection, target recognition, and environmental perception in autonomous underwater vehicles (AUVs). However, the complex underwater acoustic environment introduces various interferences, such as noise, scattering, and echo, which hinder the effectiveness of existing object detection methods in achieving satisfactory accuracy and robustness. To address these challenges in forward-looking sonar (FLS) images, we propose a novel multi-level feature aggregation network (MLFANet). Specifically, to mitigate the impact of seabed reverberation noise, we designed a low-level feature aggregation module (LFAM), which enhances key low-level image features, such as texture, edges, and contours in the object regions. Given the common presence of shadow interference in sonar images, we introduce the discriminative feature extraction module (DFEM) to suppress redundant features in the shadow regions and emphasize the object region features. To tackle the issue of object scale variation, we designed a multi-scale feature refinement module (MFRM) to improve both classification accuracy and positional precision by refining the feature representations of objects at different scales. Additionally, the CIoU-DFL loss optimization function was constructed to address the class imbalance in sonar data and reduce model computational complexity. Extensive experimental results demonstrate that our method outperforms state-of-the-art detectors on the Underwater Acoustic Target Detection (UATD) dataset. Specifically, our approach achieves a mean average precision (mAP) of 81.86%, an improvement of 7.85% compared to the best-performing existing model. These results highlight the superior performance of our method in marine environments.

With the rapid development of UAV and infrared imaging technology, the cost of UAV infrared imaging technology has decreased steadily. Small target detection technology in aerial infrared images has great potential for applications in many fields, especially in the field of traffic surveillance. Because of the low contrast and relatively limited feature information in infrared images compared to visible images, the difficulty involved in small road target detection in infrared aerial images has increased. To solve this problem, this study proposes a feature-enhanced attention and dual-GELAN net (FEADG-net) model. In this network model, the reliability and effectiveness of small target feature extraction is enhanced by a backbone network combined with low-frequency enhancement and a swin transformer. The multi-scale features of the target are fused using a dual-GELAN neck structure, and a detection head with the parameters of the auto-adjusted InnerIoU is constructed to improve the detection accuracy for small infrared targets. The viability of the method was proved using the HIT-UAV dataset and IRTS-AG dataset. According to a comparative experiment, the mAP50 of FEADG-net reached more than 90 percent, which was higher than that of any previous method and it met the real-time requirements. Finally, an ablation experiment was conducted to demonstrate that all three of the modules proposed in the method contributed to the improvement in the detection accuracy. This study not only designs a new algorithm for small road object detection in infrared remote sensing images from UAVs but also provides new ideas for small target detection in remote sensing images for other fields.

Research on Infrared Dim and Small Target Detection Algorithm Based on Low-Rank Tensor Recovery

Real-time performance and accuracy are the standards to measure the detection algorithm performance. The existing detection methods for forward-looking sonar target image are difficult to achieve ideal balance between the two standards. Due to the influence of background interference and non-rigid deformation, it hardly obtains the high detection accuracy in fast detection. In this paper, we propose a Mobilenetv3-YOLOv4-Sonar algorithm, which is a more accurate and lightweight target detection model. The backbone of YOLOv4 adopts Mobilenetv3, which is improved by Convolutional Block Attention Module (CBMA) and modified Squeeze-and-Excitation Network (SENet). Consequently, we can eliminate the influence of high-light background interference and reduce the complexity of the model. Meanwhile, the improved SPPnet is used as the neck of YOLOv4 to reduce the failure of target detection caused by non-rigid deformation. Extensive experiments and comparisons with state-of-arts detectors illustrate that the accuracy of our model has increased by 4.6% compared with YOLOv4 on the dataset, and the model parameters are only one tenth of the traditional YOLOv4, which has practical significance for target detection in forward-looking sonar images.

The increasing number of space targets has a serious impact on the space environment and spacecraft safety. In this paper, aiming at the space-based optical monitoring platform, the problem of weak and small target detection under complex background star images is studied, and the effective separation method of space targets under star points is discussed. Based on the relatively constant topological relationship of stars between sequence frames, a space target detection algorithm based on invariant star topology information is proposed, which quantifies the invariant information into iso-interior angle descriptions, and designs a target and star separation strategy. The experimental results show that the method can make full use of image information, realize fast real-time detection of multiple targets, and reduce the false alarm rate to 16.3% of the original method, which provides a new method for space-based optical target detection.

In the field of infrared remote sensing, the problem of IR small target detection is still an important component part. Concerning infrared dim small target (IRDST) detection, firstly the infrared image is processed with DWT method to get the wavelet coefficients image, but the distribution characteristics, such as scales, frequencies, orientations of wavelet coefficients in different sub-bands are various, so wavelet image denoised by a single threshold criterion can not give a satisfying estimation. Based on this motivation, a spatially adaptive multi-model de-noising strategy (SAMMDS) based IRDST detection method is proposed in this paper, which can adjust thresholding strategy according to the distribution of noise in different scales and directions. Spatially adaptive BayesShrink (SABS) thresholding, traditional BayesShrink (BS) thresholding and generalized cross validation (GCV) thresholding are all adopted here to process each sub-band separately. After reconstructing the denoised wavelet image, a simple global thresholding is used to separate the background and target finally. Experimental results demonstrate that the proposed algorithm performs better than other typical wavelet methods for small target detection with various complex backgrounds.

Dim and small infrared target fast detection guided by visual saliency

In order to solve the problem of detection and tracking of maneuvering weak targets by aerial sonobuoys, a track-before-detect method based on stochastic parabolic Hough transform was constructed. The azimuth measurement of the target was cross-located by the adaptive correlation detection buoy group, and the corresponding position information in the target measurement was obtained. The stochastic parabolic Hough transform method was used to convert the target expansion measurement to the parameter space, and the target's maneuvering track was accumulated in the parameter space. The traditional random parabolic Hough transform method was improved by means of azimuth transformation to reduce the computational complexity of the algorithm. The problem of passive detection of maneuvering weak targets was transformed into a track detection problem based on random parabolic Hough transform under the track-before-detect model, which reduces the missed track detection of weak targets with low signal-to-noise ratio. The simulation results show that the detection probability exceeds 70 % when the signal-to-noise ratio is greater than 5 dB.

To detect small infrared targets under the condition of dense clutters, we propose a single-frame target detection algorithm based on a small bounding-box filter, which is characterized by good adaptability to the position and size of a small target. During the small target detection process, the proposed algorithm first searches for the local maximum gray pixel and then, a set of concentric bounding boxes whose center is the pixel found in the first step is constructed, and the detection thresholds of a neighboring region of this pixel are calculated based on the bounding boxes. Finally, the minimum threshold is used to detect small target pixels in the neighboring region. A fast version of the proposed algorithm is a minimum bounding-box filter, which can be implemented by dividing an image into blocks and using the mid-range and range to assess the concentration trend and dispersion of the background. Simulation and analysis results show that the proposed algorithm can achieve high detection probability and low false alarm rate when detecting small targets in the complex background; while its fast version has high computational efficiency. The proposed algorithm can be used in infrared searching and tracking systems.