Robust Target Detection Research Articles

Automatic Target Detection Using Ground Penetrating Radar (GPR) Data Based on A Machine Learning Approach: A Survey

Ground Penetrating Radar (GPR) is a valuable tool for subsurface exploration across diverse fields such as archaeology, defence, and civil engineering. Traditionally, GPR data has been interpreted manually, requiring extensive expertise and being time-consuming. Recently, machine- learning approaches have emerged as effective solutions for automating target detection, significantly reducing time and human dependency while enhancing accuracy. This review provides a comprehensive overview of the current advancements in automatic target detection using GPR data, focusing on machine learning-based methods. We summarize feature extraction techniques, popular machine learning algorithms, and challenges within this domain. This paper also identifies future directions and potential improvements for robust, accurate, and efficient GPR-based automatic target detection systems. Key Words: Machine Learning, Ground Penetrating Radar, Object Detection, Signal Processing.

Fish-Finder: A robust small target detection method for aquaculture fish in low-quality underwater images.

Underwater fish object detection serves as a pivotal research direction in marine biology, aquaculture management, and computer vision, yet it poses substantial challenges due to the complexity of underwater environments, occultations, and the small-sized and frequently moving fish in aquaculture. Addressing these challenges, we propose a novel underwater fish object detection algorithm named Fish-Finder. First, we engendered a structure titled "C2fBF," utilizing the dual-path routing attention protocol of BiFormer. The primary objective of this structure is to alleviate the perturbations induced by underwater intricacies during the phase of downsampling in the backbone network, thereby discerning and conserving finer contextual features. Subsequently, we co-opted the RepGFPN method within our neck network-a distinctive approach that adeptly merges high-level semantic constructs with low-level spatial specifics, thus fortifying its multi-scale detection prowess. Then, in an endeavor to diminish the sensitivity toward positional aberrations during the detection of diminutive aquatic creatures, we incorporated a novel bounding box regression loss function, the Wasserstein loss, to the existing CIoU. This innovative function gauges the congruity between the predicted bounding box Gaussian distribution and the reference bounding box Gaussian distribution. Finally, in regard to the dataset, we independently assembled a specific dataset termed "SmallFish." This unique dataset, meticulously designed for the detection of small-scale fish within intricate underwater settings, includes 5000 annotated images of small fish. Experimental results demonstrate that, compared to the state-of-the-art detection methods, our proposed method improves the accuracy by and , and mean average precision (mAP) increases and in public dataset Kaggle-Fish and our SmallFish dataset, respectively.

Deghosting method for cross localization in distributed high frequency surface wave radar

AbstractIn this article, the challenging problem of multi‐target cross localization within a novel distributed high‐frequency surface wave radar (HFSWR) is tackled. This system consists of two transmitter‐receiver pairs, each of which can correspondingly generate a set of Range‐Doppler measurements. By associating the Range‐Doppler measurements from the same target, the individual target location can be derived using the associated measurements. However, when multiple targets are involved, it is unknown which measurements originate from the same target, leading to ambiguities in the measurement‐to‐measurement association. False associations can result in ghosts, ultimately degrading the overall system performance. To deal with the ghosts, a three‐stage deghosting method is proposed that incorporates the geometric characteristics of the system, the velocity features of the targets, and the motion features of the targets across multiple frames. The simulation results demonstrate the effectiveness of the proposed method compared with the other investigated deghosting algorithms. The proposed approach exhibits robust target detection capability while significantly reducing both the OSPA error and the cardinality error.

Hunt-inspired Transformer for visual object tracking

This paper presents a hunt-inspired Transformer for visual object tracking, dubbed as HuntFormer. The HuntFormer focuses on robust target detection and identification, simulating natural hunting processes. Specifically, the HuntFormer comprises two essential module designs including a predictor for detection and a verifier for identification. The predictor emulates the detection stage by designing a motion trajectory guided particle filter, which identifies potential target locations by predicting the motion state within a particle filtering framework. The predictor utilizes spatio-temporal correlation scores between dynamic target templates and the search region to guide the learning process to generate a set of reliable particles. This enables the base tracker to narrow its search range to focus on the target, and swiftly re-detect the target in case of model drift. Once the target is re-detected, the verifier assesses the detection result as a reliable tracked item. The verifier initially maintains a dynamic memory that stores reliable target templates and their corresponding locations in the motion trajectory. It then models the uncertainty of appearance information within this memory probabilistically. The output uncertainty score determines whether the memory gets updated or not. Ultimately, the predictor and the verifier collaborate, ensuring a robust tracking outcome. Extensive evaluations on six challenging benchmark datasets demonstrate HuntFormer’s favorable performance against various state-of-the-art trackers. Notably, in the VOT-LT2022 tracking challenge, the HuntFormer won the third place with an F-score of 0.598, closely competing for the second place with an F-score of 0.600.

A Robust Target Detection Algorithm Based on the Fusion of Frequency-Modulated Continuous Wave Radar and a Monocular Camera

Decision-level information fusion methods using radar and vision usually suffer from low target matching success rates and imprecise multi-target detection accuracy. Therefore, a robust target detection algorithm based on the fusion of frequency-modulated continuous wave (FMCW) radar and a monocular camera is proposed to address these issues in this paper. Firstly, a lane detection algorithm is used to process the image to obtain lane information. Then, two-dimensional fast Fourier transform (2D-FFT), constant false alarm rate (CFAR), and density-based spatial clustering of applications with noise (DBSCAN) are used to process the radar data. Furthermore, the YOLOv5 algorithm is used to process the image. In addition, the lane lines are utilized to filter out the interference targets from outside lanes. Finally, multi-sensor information fusion is performed for targets in the same lane. Experiments show that the balanced score of the proposed algorithm can reach 0.98, which indicates that it has low false and missed detections. Additionally, the balanced score is almost unchanged in different environments, proving that the algorithm is robust.

AI‐Assisted Design of Printed Edge‐Fed Non‐Uniform Zig‐Zag Antenna for mm‐Wave Automotive Radar

AbstractIn this paper, the design of a novel horizontally polarized single‐layer antenna for 77 (GHz) automotive radar applications is4 addressed. An innovative non‐uniform zig‐zag parametrization of the antenna layout is considered to enable a more flexible control on both the impedance matching in the working frequency band and the shaping of the radiated beam pattern with respect to a standard (uniform) one without compromising the linear (horizontal) polarization of the radiated field. Such a polarization guarantees a lower back‐scattering from road pavements, resulting in a reduced amount of clutter and thus allowing a more robust target detection. Moreover, the single‐layer layout has several advantages in terms of fabrication simplicity/costs and mechanical robustness to vibrations. The design of the proposed non‐uniform zig‐zag antenna (NZA) is performed through a customized implementation of the System‐by‐Design (SbD) approach that fruitfully combines machine learning and evolutionary optimization to efficiently deal with the computational complexity at hand. An extensive numerical validation, dealing with designs of different lengths, verifies the high performance of the NZA in terms of beam direction deviation (e.g., BDD < 1 (deg)), sidelobe level (e.g., SLL < −18.2 (dB)), and polarization ratio (e.g., PR > 20 (dB)) within the working frequency band (GHz), as well as its superiority over competitive designs. Finally, the realization of a prototype and its experimental test, validate the proposed NZA concept for automotive mm‐wave radar applications in advanced driver assistance systems and autonomous vehicles such as, for instance, adaptive cruise control, collision avoidance, and blind spot detection.

Target Detection in Challenging Environments: Photonic Radar with a Hybrid Multiplexing Scheme for 5G Autonomous Vehicles

The rapid deployment of 5G autonomous vehicles has placed a premium on low-latency communication and reliable sensor technologies for the real-time mapping of road conditions, aligning with sustainability objectives in transport. In response to this imperative, photonic-based radar systems have emerged as an increasingly attractive solution, characterized by their low power consumption and cost-effectiveness. This study delves into the application of linear frequency-modulated continuous wave (FMCW) techniques within photonic radar sensors for the precise detection of multiple targets. Our proposed system seamlessly integrates mode-division multiplexing (MDM) and polarization-division multiplexing (PDM) to achieve a robust target detection capability, contributing to sustainable traffic management. To assess its effectiveness, we rigorously evaluated the system’s performance under challenging conditions, marked by a high atmospheric attenuation of 75 dB/km and a low material reflectivity of 20%. Our results unequivocally demonstrate the efficacy of the MDM-PDM photonic radar in successfully detecting all four specified targets, underscoring its potential to enhance road safety in the realm of autonomous vehicles. The adoption of this technology supports sustainable mobility by mitigating human errors and optimizing the real-time mapping of road conditions.

Robust target detection of intelligent integrated optical camera and mmWave radar system

Target detection is pivotal for modern urban computing applications. While image-based techniques are widely adopted, they falter under challenging environmental conditions such as adverse weather, poor lighting, and occlusion. To improve the target detection performance under complex real-world scenarios, this paper proposes an intelligent integrated optical camera and millimeter-wave (mmWave) radar system. Utilizing both physical knowledge and data-driven methods, a long-term robust radar-camera fusion algorithm is proposed to solve the heterogeneous data fusion problem for detection improvement. For the occlusion scenarios, the proposed algorithm can effectively detect occluded targets with the help of memory through performing long-term detection. For dark scenarios with low-light conditions, the proposed algorithm can effectively mark the target in the dark picture as well as provide rough stickman imaging. The above two innovative functions of the hybrid optical camera and mmWave radar system are tested in real-world scenarios. The results demonstrate the robustness and significant enhancement in the target detection performance of our integrated system.

Evaluating the Performance of a Dual-Frequency Multibeam Echosounder for Small Target Detection

With rising interest in marine renewable energy (MRE) associated with offshore wind, waves, and tidal flows, the effects of device placement on changes in animal behaviour require proper assessment to minimise environmental impacts and inform decision making. High-frequency multibeam echosounders, or imaging sonars, can be used to observe and record the underwater movement and behaviour of animals at a fine scale (tens of metres). However, robust target detection and tracking of closely spaced animals are required for assessing animal–device and predator–prey interactions. Dual-frequency multibeam echosounders combine longer detection ranges (low frequency) with greater detail (high frequency) while maintaining a wide field of view and a full water column range compared to acoustic or optical cameras. This study evaluates the performance of the Tritech Gemini 1200ik imaging sonar at 720 kHz (low frequency) and 1200 kHz (high frequency) for small target detection with increasing range and the ability of the two frequency modes to discriminate between two closely spaced targets using a 38.1 mm tungsten carbide acoustic calibration sphere under controlled conditions. The quality of target detection decreases for both modes with increasing range, with a 25 m limit of detection at high frequency and a low-frequency mode able to detect the target up to 30 m under test conditions in shallow water. We quantified the enhanced performance of the high-frequency mode in discriminating targets at short ranges and improved target detection and discrimination at high ranges in the low-frequency mode.

B-243 Utilizing Lyophilized LAMP Reagents in Rapid Molecular Assays

Abstract Background Loop Mediated Isothermal Amplification (LAMP) has become a widely used method for detection of target nucleic acids (DNA and RNA) as it offers a robust and simple alternative to PCR. LAMP is particularly well suited to point of care (POC) applications such as COVID-19 diagnostics because only a single incubation temperature is required for nucleic acid amplification and the technology is compatible with simple detection strategies, including colorimetric or lateral flow readouts. To further increase the utility of LAMP in POC molecular diagnostic workflows, elimination of cold chain requirements for reagent shipment and storage is desired. In this study, we investigate single and multiplex detection of several viral infectious diseases using lyophilized RT-LAMP reagents. Methods Assays targeting SARS-CoV-2, FluA, FluB and a host control nucleic acid were evaluated using various detection methods with lyophilized RT-LAMP reagents. Compatibility was established with endpoint LAMP detection strategies, such as colorimetric dyes, and real time multiplex LAMP detection, which is increasingly finding utility in POC testing for common respiratory infections that present with similar symptoms. Results Assays employing lyophilized RT-LAMP reagents maintained robust detection of viral respiratory targets within 30 min at 65°C using various detection strategies. Colorimetric dyes such as eriochrome back T and calcein resulted in successful visual readout upon amplification while, one prominent colorimetric dye, hydroxy naphthol blue, was found to be incompatible with the lyophilized reagents used in the study. Additionally, simple hybridization probes permitted simultaneous detection of SARS-CoV-2, FluA and FluB in a single reaction. Conclusion LAMP is a robust, simple, isothermal amplification strategy that continues to enable testing beyond traditional laboratory settings. Lyophilized reagents extend the utility of LAMP in POC settings regardless of the detection strategy and will be important factors in the extension of this powerful molecular diagnostic tool to decentralized, field, and at-home testing applications.

Infrared small target detection based on local-image construction and maximum correntropy

Infrared small target detection has been widely applied in the civil and military fields, but is hard to deal with complex background and highlight edge. To achieve fast and robust target detection, a novel strategy is proposed in this paper. Initially, the local-image method is used to construct a single-frame infrared image into a low-rank sparse matrix with close spatial relevance. Then, the sparse matrix based on maximum correntropy is used to express the small target, which is applied to the improved bilateral random projection method to achieve more robust and faster decomposition for small target. Finally, in order to achieve better convergence result, the prominent edge structure tensor for infrared image is designed and separated from the sparse matrix of target. Extensive experimental results show that the proposed algorithm is obviously superior to other methods in running time and detection rate, especially for highlight cluster.

Multi-stage morphological operators for small infrared target detection

Infrared small target detection is a challenging task. Despite the recent advances in the development of small infrared target detection algorithms, having a robust target detection algorithm with high probability of detection rate remains unaddressed. To this end, in this paper, a morphological top-hat transform is presented. The proposed method benefits from intrinsic high probability detection rate of classical top-hat transform, while the false alarm rate remains below the acceptable threshold. Also, the sensitivity to noise analysis demonstrates that the proposed method is robust against various noise intensities. The proposed method is tested on some real infrared images. The experiments show that the proposed method outperforms state-of-the-arts in both quantitative and qualitative manners.

Small Aerial Target Detection Using Trajectory Hypothesis and Verification

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 IMU assisted inter-frame 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.

Infrared Small Target Detection Algorithm Using an Augmented Intensity and Density-Based Clustering

In infrared search and tracking (IRST) systems, small target detection is challenging because IR imaging lacks feature information and has a low signal-to-noise ratio. The recently studied small IR target detection methods have achieved high detection performance without considering execution time. We propose a fast and robust single-frame IR small target detection algorithm while maintaining excellent detection performance. The augmented infrared intensity map based on the standard deviation speeds up small target detection and improves detection accuracy. Density-based clustering helps to detect the shape of objects and makes it easy to identify centroid points. By incorporating these two approaches, the proposed method has a novel approach to the small target detection algorithm. We have self-built 300 images with various scenes and experimented with comparing other methods. Experimental results demonstrate that the proposed method is suitable for real-time detection and effective even when the target size is as small as 2 pixels.

Infrared Single-Frame Small Target Detection Based on Block-Matching.

The robust detection of small targets is one of the crucial techniques in an infrared system. It is still a challenge to detect small targets under complex backgrounds. Aiming at the problem where infrared small target detection is easily disturbed by complex backgrounds, an infrared single frame detection method based on a block-matching approach is proposed in this paper. Firstly, the input infrared image is processed by extracting blocks from it. A new infrared model is constructed by finding blocks that are similar to each such block. Then, the small target detection based on the block-matching model is formulated as an optimization problem of recovering low-rank and sparse matrices, which are effectively solved using robust principal component analysis. Finally, the results of processing are reconstructed to obtain the target and background images. A simple segmentation method is used to segment the target image. The experimental results from the actual infrared sequences show that the proposed method has better background suppression ability under complex backgrounds and better detection performance than conventional baseline methods.

Multiscale contrast enhancement method for small infrared target detection

Infrared search and track (IRST) systems have been applied extensively in the civil and military fields. However, fast, effective, and robust dim and small infrared target detection remains a challenging research topic. Dim and small targets are easily obscured in different backgrounds or noises, which results in a high false alarm rate. A novel strategy is proposed for small infrared target detection to achieve a high true positive rate and robust detection. First, the prominent edge structures of the original image are obtained by constructing a structure tensor. Subsequently, a Gaussian bandpass filter with multiscale windows is used to obtain an infrared image that contains complex edges and small targets. An infrared image with an enhanced signal-to-clutter ratio is achieved by combining with the two methods, whereby the noise can be effectively reduced. Thereafter, candidate regions that contain the target and a smaller number of edges with higher brightness than that of the target are obtained using relaxed threshold segmentation. Finally, a Gaussian gradient contrast method is proposed in which the highlighted edges are removed so that only small infrared targets remain. Extensive experimental results demonstrate that the proposed method can achieve a significant optimization of the true positive and false alarm rates, as well as improved efficiency and robustness.

Jammer robust model-aided deep learning-based target detection for cognitive sonar

This work extends the development of an adaptive deep learning-based target detection algorithm for a channel matrix-based cognitive sonar framework that makes use of both a primary and secondary dataset. The channel matrix-based framework models all waveform dependent components, i.e. the sonar echo and clutter, via transfer function matrices, whereas all other waveform independent noise is characterized via the data covariance. By leveraging "lessons learned" from a derived model-based generalized likelihood ratio test (GLRT), a data driven deep learning algorithm was made adaptive to waveform dependent clutter returns in our previous work. The algorithm, however, remains fragile to waveform independent jamming and interference, and the extensive training required to obtain robust performance is practically infeasible. Thus, in this work further modifications are included to robustify the algorithm against these waveform independent components by leveraging knowledge from the model-based GLRT. The performance of the proposed algorithm is tested using various scenarios with jamming and interference signals.

Robust and Fair Undersea Target Detection with Automated Underwater Vehicles for Biodiversity Data Collection

Undersea/subsea data collection via automated underwater vehicles (AUVs) plays an important role for marine biodiversity research, while it is often much more challenging than the data collection above ground via satellites or AUVs. To enable the automated undersea/subsea data collection system, the AUVs are expected to be able to automatically track the objects of interest through what they can “see” from their mounted underwater cameras, where videos or images could be drastically blurred and degraded in underwater lighting conditions. To solve this challenge, in this work, we propose a cascaded framework by combining a DCGAN (deep convolutional generative adversarial network) with an object detector, i.e., single-shot detector (SSD), named DCGAN+SSD, for the detection of various underwater targets from the mounted camera of an automated underwater vehicle. In our framework, our assumption is that DCGAN can be leveraged to alleviate the impact of underwater conditions and provide the object detector with a better performance for automated AUVs. To optimize the hyperparameters of our models, we applied a particle swarm optimization (PSO)-based strategy to improve the performance of our proposed model. In our experiments, we successfully verified our assumption that the DCGAN+SSD architecture can help improve the object detection toward the undersea conditions and achieve apparently better detection rates over the original SSD detector. Further experiments showed that the PSO-based optimization of our models could further improve the model in object detection toward a more robust and fair performance, making our work a promising solution for tackling the challenges in AUVs.

A Cascade Defense Method for Multidomain Adversarial Attacks under Remote Sensing Detection

Deep neural networks have been widely used in detection tasks based on optical remote sensing images. However, in recent studies, deep neural networks have been shown to be vulnerable to adversarial examples. Adversarial examples are threatening in both the digital and physical domains. Specifically, they make it possible for adversarial examples to attack aerial remote sensing detection. To defend against adversarial attacks on aerial remote sensing detection, we propose a cascaded adversarial defense framework, which locates the adversarial patch according to its high frequency and saliency information in the gradient domain and removes it directly. The original image semantic and texture information is then restored by the image inpainting method. When combined with the random erasing algorithm, the robustness of detection is further improved. Our method is the first attempt to defend against adversarial examples in remote sensing detection. The experimental results show that our method is very effective in defending against real-world adversarial attacks. In particular, when using the YOLOv3 and YOLOv4 algorithms for robust detection of single-class targets, the AP60 of YOLOv3 and YOLOv4 only drop by 2.11% and 2.17%, respectively, under the adversarial example.

Gradient field divergence-based small target detection in infrared images

Infrared small target detection in complex cloud backgrounds has long been a research challenge. A novel robust target detection method based on the divergence of gradient field is proposed to enhance the target and suppress the complex background synchronously. The negative gradient field of the target intensity (NIG field) matches with characteristics of the positive source. The cloud cluster, on the other hand, lacks this feature. First, the NIG field is calculated based on the target’s property from the original image. The divergence values of NIG field are then calculated to produce a defined divergence map (D map), which highlights the target regions while suppressing the clutter regions. Meanwhile, a local vectors angle measure (LVAM) operator of the NIG field is designed to measure the angle distribution of 8-neighbour vectors and eliminate false target areas. Then, the defined local angle map (LA map) is obtained by measuring the local angle value of 8-neighbour vectors for each patch of NIG field. In addition, the divergence-local angle map (D-LA map) is obtained as the Hadamard product of the D map and LA map. Finally, we can easily obtain the target via a constant false alarm ratio based on the D-LA map. The performance evaluation results of real image sequences show that the proposed method is satisfactory for clutter suppression and target detection. Moreover, the results from comparative experiments show that the proposed method outperforms conventional methods in terms of detection accuracy and false alarm rate.