Target Detection Results Research Articles

K-means adaptive 2DSSA based on sparse representation model for hyperspectral target detection

Target detection is a hot spot in hyperspectral imagery (HSI) processing. The detection accuracy of target detection algorithms based on sparse representation (SR) models usually suffers from the high reconstruction residuals caused by inaccurate background estimations and insufficient target samples. Besides, with the development of hyperspectral imaging technology, the spatial resolution of HSI has been continuously enhanced, which can provide more spatial information for target detection. However, spatial information is often overlooked, leading to the underutilization of the pluralistic features of HSI. Target detection using only spectral information is susceptible to spectral variation, resulting in a high false alarm rate. To alleviate these problems, this paper proposes a joint spatial-spectral algorithm. In terms of spectra, a dictionary construction strategy (DCS) is designed for the sparse representation-based binary hypothesis (SRBBH) detector to reduce reconstruction residuals of target and background samples. In terms of space, k-means 2D adaptive singular spectrum analysis (KSSA) is used to extract spatial features in cluster units. Using spatial features can enhance the robustness of the algorithm to spectral variation, thereby reducing false alarms. The target detection results are obtained by applying DCS-SRBBH to the KSSA feature image. We evaluate the proposed algorithm on three datasets: two public and one of our own. Comprehensive experimental results indicate that the proposed algorithm outperforms other target detection algorithms in terms of accuracy.

PD-DETR: towards efficient parallel hybrid matching with transformer for photovoltaic cell defects detection

Defect detection for photovoltaic (PV) cell images is a challenging task due to the small size of the defect features and the complexity of the background characteristics. Modern detectors rely mostly on proxy learning objectives for prediction and on manual post-processing components. One-to-one set matching is a critical design for DEtection TRansformer (DETR) in order to provide end-to-end capability, so that does not need a hand-crafted Efficient Non-Maximum Suppression NMS. In order to detect PV cell defects faster and better, a technology called the PV cell Defects DEtection Transformer (PD-DETR) is proposed. To address the issue of slow convergence caused by DETR’s direct translation of image feature mapping into target detection results, we created a hybrid feature module. To achieve a balance between performance and computation, the image features are passed through a scoring network and dilated convolution, respectively, to obtain the foreground fine feature and contour high-frequency feature. The two features are then adaptively intercepted and fused. The capacity of the model to detect small-scale defects under complex background conditions is improved by the addition of high-frequency information. Furthermore, too few positive queries will be assigned to the defect target via one-to-one set matching, which will result in sparse supervision of the encoder and impair the decoder’s ability of attention learning. Consequently, we enhanced the detection effect by combining the original DETR with the one-to-many matching branch. Specifically, two Faster RCNN detection heads were added during training. To maintain the end-to-end benefits of DETR, inference is still performed using the original one-to-one set matching. Our model implements 64.7% AP on the PVEL-AD dataset.

Dual-Structure Elements Morphological Filtering and Local Z-Score Normalization for Infrared Small Target Detection against Heavy Clouds

Infrared (IR) small target detection in sky scenes is crucial for aerospace, border security, and atmospheric monitoring. Most current works are typically designed for generalized IR scenes, which may not be optimal for the specific scenario of sky backgrounds, particularly for detecting small and dim targets at long ranges. In these scenarios, the presence of heavy clouds usually causes significant false alarms due to factors such as strong edges, streaks, large undulations, and isolated floating clouds. To address these challenges, we propose an infrared dim and small target detection algorithm based on morphological filtering with dual-structure elements. First, we design directional dual-structure element morphological filters, which enhance the grayscale difference between the target and the background in various directions, thus highlighting the region of interest. The grayscale difference is then normalized in each direction to mitigate the interference of false alarms in complex cloud backgrounds. Second, we employ a dynamic scale awareness strategy, effectively preventing the loss of small targets near cloud edges. We enhance the target features by multiplying and fusing the local response values in all directions, which is followed by threshold segmentation to achieve target detection results. Experimental results demonstrate that our method achieves strong detection performance across various complex cloud backgrounds. Notably, it outperforms other state-of-the-art methods in detecting targets with a low signal-to-clutter ratio (MSCR ≤ 2). Furthermore, the algorithm does not rely on specific parameter settings and is suitable for parallel processing in real-time systems.

Enhanced-YOLOv8: A new small target detection model

Small target detection is a very difficult task and remains one of the most challenging problems in computer vision due to variations in object shape, appearance and position, as well as the effects of lighting and occlusion during imaging. To improve the accuracy of the small target detection results, we propose a new small target detection model, Enhanced-YOLOv8. Firstly, a small target detection level (STDL) is added to the original effective feature layer of YOLOv8, which not only provides richer semantic information but also get more accurate target localization and bounding box accuracy. When detecting small targets, the detection accuracy can be improved by more detailed information. Then, the fusion convolutional block attention module (FCBAM) is proposed by introducing the position attention module (PAM) based on the traditional CBAM. FCBAM not only can adaptively select and fuse the most representative features, but also can better capture the image important features at different positions in the image and enhance spatial detail perception. Finally, semantic fusion network (SFN) is proposed on the basis of residual network, which introduces semantic information of high-layer feature into low-layer feature. It can adaptively guide the fusion of high-layer feature and low-layer feature to reduce the loss of feature information. After experimental verification, the Enhanced-YOLOv8 proposed improves the accuracy of the detection results.

Mapping Geothermal Indicator Minerals Using Fusion of Target Detection Algorithms

Mineral mapping from satellite images provides valuable insights into subsurface mineral alteration for geothermal exploration. In previous studies, eight fundamental algorithms were used for mineral mapping utilizing USGS spectra, a collection of reflectance spectra containing samples of minerals, rocks, and soils created by the USGS. We used an ASD FieldSpec 4 Hi-RES NG portable spectrometer to collect spectra for analyzing ASTER images of the Coso Geothermal Field. Then, we established the ground-truth information and the spectral library by analyzing 97 samples. Samples collected from the field were analyzed using the CSIRO TSG (The Spectral Geologist of the Commonwealth Scientific and Industrial Research Organization). Based on the mineralogy study, multiple high-purity spectra of geothermal alteration minerals were selected from collected data, including alunite, chalcedony, hematite, kaolinite, and opal. Eight mineral spectral target detection algorithms were applied to the preprocessed satellite data with a proposed local spectral library. We measured the highest overall accuracy of 87% for alunite, 95% for opal, 83% for chalcedony, 60% for hematite, and 96% for kaolinite out of these eight algorithms. Three, four, five, and eight algorithms were fused to extract mineral alteration with the obtained target detection results. The results prove that the fusion of algorithms gives better results than using individual ones. In conclusion, this paper discusses the significance of evaluating different mapping algorithms. It proposes a robust fusion approach to extract mineral maps as an indicator for geothermal exploration.

Research on Object Detection in Animal Images Based on Convolutional Neural Networks

Abstract Object detection is the use of computer to find out all the objects of interest in the image, determine their categories and locations, is one of the core problems in the field of computer vision. Traditional animal image target detection usually adopts the sliding window method, but due to the different sizes of the input images, this method has some problems such as insufficient training samples, low detection accuracy and slow speed. In order to solve such problems, based on the development of deep learning in recent years, this paper proposes an object detection algorithm based on convolutional neural network. YOLOv5 was used to effectively distinguish, identify and mark animal categories, which accelerated the training of the model and greatly improved the accuracy of target detection. Through the analysis of experimental data, it was concluded that the algorithm studied in this paper had good performance and good target detection results. Finally, the key problems of object detection research are summarized, and the future development trend of this field is prospected. When the number of training rounds is 30, the accuracy rate has reached about 70%, and after 50 rounds of training, some accuracy can reach 90%, which is excellent and better than other traditional algorithms.

Improved Traffic Small Object Detection via Cross-Layer Feature Fusion and Channel Attention

Small object detection has long been one of the most formidable challenges in computer vision due to the poor visual features and high noise of surroundings behind them. However, small targets in traffic scenes encompass a multitude of complex visual interfering factors, bearing crucial information such as traffic signs, traffic lights, and pedestrians. Given the inherent difficulties faced by generic models in addressing these issues, we conduct a comprehensive investigation on small target detection in this application scenario. In this work, we present a Cross-Layer Feature Fusion and Channel Attention algorithm based on a lightweight YOLOv5s design for traffic small target detection, named CFA-YOLO. To enhance the sensitivity of the model toward vital features, we embed the channel-guided Squeeze-and-Excitation (SE) block in the deep layer of the backbone. Moreover, the most excellent innovation of our work belongs to the effective cross-layer feature fusion method, which maintains robust feature fusion and information interaction capabilities; in addition, it simplifies redundant parameters compared with the baseline model. To align with the output features of the neck network, we adjusted the detection heads from three to two. Furthermore, we also applied the decoupled detection head for classification and bounding box regression tasks, respectively. This approach not only achieves real-time detection standards, but also improves the overall training results in parameter-friendly manner. The CFA-YOLO model significantly pays a lot of attention to the detail features of small targets, thereby it also has a great advantage in addressing the issue of poor performance in traffic small target detection results. Vast experiments have validated the efficiency and effectiveness of our proposed method in traffic small object detection. Compared with the latest lightweight detectors, such as YOLOv7-Tiny and YOLOv8s, our method consistently achieves superior performance both in terms of the model’s accuracy and complexity.

Environment Modeling Method for Intelligent Robots Based on Binocular Vision

With the development of technology, the demand for intelligent mobile robots is growing steadily. Environment perception and modeling, are the key elements to achieve robot intelligence. Therefore, binocular stereo vision sensor is used as the core device to perform operations such as binocular camera calibration, obtaining binocular camera internal/external parameters, and distortion correction. On this basis, a multi-dimensional and all-round environment perception system is constructed, and the dynamic target detection results and 3D scene map reconstruction results are displayed dynamically in real time. The experimental results of binocular camera calibration show that the re-projection error lies in the sub-pixel interval, and the image distortion caused by the camera is basically eliminated to meet the experimental expectation of distortion correction; the experimental results of environment modeling show that the mean value of deviation between the object representation value of 3D scene map and the actual object real value is -0.041m, among which the minimum deviation value is 0.001m and the maximum deviation value is 0.532m, in The experimental results are excellent in the tasks of 3D scene map reconstruction and feature point matching. In addition, the storage space of 3D scene map is significantly reduced, and the real-time performance of the system is significantly better than the traditional method.

Hyperspectral Target Detection Methods Based on Statistical Information: The Key Problems and the Corresponding Strategies

Target detection is an important area in the applications of hyperspectral remote sensing. Due to the full use of information of the target and background, target detection algorithms based on the statistical characteristics of an image are always occupy a dominant position in the field of hyperspectral target detection. From the perspective of statistical information, we firstly presented detailed discussions on the key factors affecting the target detection results, including data origin, target size, spectral variability of target, and the number of bands. Further, we gave the corresponding strategies for several common situations in the practical target detection applications.

Multi-object tracking for horse racing

Multi-object tracking has been extensively studied in pedestrian behavior analysis and vehicle analysis, but has yet to be well extended to the more challenging horse racing scenarios. This work makes the first attempt to systematically analyze challenges for horse racing tracking problems, including occlusion, trajectory staggered, often switching of cameras (i.e., angles of views), and blurred sprint caused by horse competition. An augmentation-based multi-object tracking method (GMOT) is proposed to solve the above-mentioned challenges. The auxiliary classifier generative adversarial network is adopted in GMOT to augment the horse racing data to enhance target detection and re-identification results. Horse racing videos recorded in day and night scenes are both tested in our experiments. Experimental results show that the proposed method yields good results.

Development of feature extraction method based on interval-valued Pythagorean fuzzy decision theory

Feature extraction is an important step in image processing and the accuracy of the extraction affects the result of subsequent target detection. There are many feature extraction algorithms, but there are few theories and methods about the accuracy of the extraction. Moreover, most of the existing extraction methods are computationally complex, and they will expose deficiencies once they encounter a large number of standard cases. In order to fill this gap, this study proposes a new soft computing multi-criteria group decision-making (MCGDM) method based on interval-valued Pythagorean fuzzy set information to deal with situations where multiple criteria are involved in complex decisions. Thus, the power average operator is used to eliminate the effects of unreasonable input arguments on decision-making results, and the Maclaurin symmetric mean operator is used to comprehensively consider the mutual relationship between input arguments in this article. Combining with the concept of IVPFS, the interval-valued Pythagorean fuzzy power Maclaurin symmetric mean (IVPFPMSM) operator and weighted IVPFPMSM operator are proposed. Then, the TOPSIS method is used to determine the weight vector of decision-making set, and a MCGDM method is developed under the interval-valued Pythagorean fuzzy framework. Next, aiming at the defects of the existing evaluation criteria, we consider the different ranges of membership degree and non-membership degree to propose a new evaluation criterion of MCGDM method. Finally, the proposed method is applied to the optimal selection of characteristic interval of foreign fibers to verify its practicability and effectiveness. The proposed method has certain guiding significance for the extension of decision-making fuzzy operators and the exploration of feature extraction methods.

Vehicle door frame positioning method for binocular vision robots based on improved YOLOv4

In the task of using robots to capture end-of-life cars, the position of the vehicle door frame needs to be grasped. A fast and accurate positioning of the vehicle door frame is the key to realizing the automatic car grasping process. Traditional methods for locating and grasping scrap cars rely heavily on manual operations and suffer from low grasping efficiency and poor accuracy. Therefore, this paper proposes a binocular vision robot vehicle door frame spatial localization method based on the improved YOLOv4. This method includes a lightweight and efficient feature fusion target detection network in complex environments, and the target detection results are combined with an enhanced SURF feature–matching method to locate the vehicle door frame position. To simplify the network structure, MobileNetv3 is used instead of the backbone network CSPDarknet53, and deep separable convolution is used in the network. To increase the sensitivity of the network to vehicle door frame targets in complex environments, an improved convolutional block attention module is added to the pyramid attention with simple network backbones. Moreover, adaptive spatial feature fusion is introduced into the network to fully use the features at different scales for more effective feature fusion. Compared with YOLOv4, the number of network parameters is reduced by 73.8%, the mAP is improved by 1.35%, and the detection speed is increased by 28.7%. The experimental results demonstrate that the positioning accuracy of the system is 0.745 mm, which meets the positioning measurement error of less than 1 cm required for the vehicle door frame. The paper also compares our findings with other network models. The results show that the method achieves a good balance between detection speed and detection accuracy, satisfying the task of identifying vehicle door frames in complex environments with good detection results.

3D semantic map construction based on point cloud and image fusion

AbstractAccurate and robust positioning and mapping are the core functions of autonomous mobile robots, and the ability to analyse and understand scenes is also an important criterion for the intelligence of autonomous mobile robots. In the outdoor environment, most robots rely on GPS positioning. When the signal is weak, the positioning error will interfere with the mapping results, making the semantic map construction less robust. This research mainly designs a semantic map construction system that does not rely on GPS signals for large outdoor scenes. It mainly designs a feature extraction scheme based on the sampling characteristics of Livox‐AVIA solid‐state LiDAR. The factor graph optimisation model of frame pose and inertial measurement unit (IMU) pre‐integrated pose, using a sliding window to fuse solid‐state LiDAR and IMU data, fuse laser inertial odometry and camera target detection results, refer to the closest point distance and curvature for semantic information. The point cloud is used for semantic segmentation to realise the construction of a 3D semantic map in outdoor scenes. The experiment verifies that laser inertial navigation odometry based on factor map optimisation has better positioning accuracy and lower overall cumulative error at turning, and the 3D semantic map obtained on this basis performs well.

An improved YOLOv5 algorithm for obscured target recognition

Target detection is an important problem in computer vision and has important research value in the fields of pedestrian tracking, license plate recognition, and unmanned vehicles [1].The Viola-Jones algorithm is used to detect frontal face images, which improves the speed of face detection by tens or hundreds of times while obtaining the same or even better accuracy, but for special and HOG captures local shape information better and has good invariance to both geometric and optical changes, SVM solves machine learning in small sample cases, but its feature descriptor acquisition process is complex and has high dimensionality, leading to poor real-time performance, and the support vector machine algorithm is difficult to implement for large-scale training samples, while the deep learning-based YOLOv5 target detection algorithm combines the advantages of Viola-Jones algorithm and HOG+SVM algorithm to make up for the shortcomings of the above two algorithms, which is not only very stable for occlusion and complex case processing, but also can be implemented for large regular training samples, but the accuracy of YOLOv5 for target detection is not ideal, and this paper adds SENet mechanism in YOLOv5, which can make the network better to learn the locations in the images that need attention. Therefore, this paper first introduces the traditional target detection algorithm, then introduces and analyzes the Yolov5 algorithm, and improves and optimizes it, and compares it with the traditional target detection algorithm, and the results show that the improved Yolov5 algorithm has better results for target detection.

Long-Strip Target Detection and Tracking with Autonomous Surface Vehicle

As we all know, target detection and tracking are of great significance for marine exploration and protection. In this paper, we propose one Convolutional-Neural-Network-based target detection method named YOLO-Softer NMS for long-strip target detection on the water, which combines You Only Look Once (YOLO) and Softer NMS algorithms to improve detection accuracy. The traditional YOLO network structure is improved, the prediction scale is increased from threeto four, and a softer NMS strategy is used to select the original output of the original YOLO method. The performance improvement is compared totheFaster-RCNN algorithm and traditional YOLO methodin both mAP and speed, and the proposed YOLO–Softer NMS’s mAP reaches 97.09%while still maintaining the same speed as YOLOv3. In addition, the camera imaging model is used to obtain accurate target coordinate information for target tracking. Finally, using the dicyclic loop PID control diagram, the Autonomous Surface Vehicle is controlled to approach the long-strip target with near-optimal path design. The actual test results verify that our long-strip target detection and tracking method can achieve gratifying long-strip target detection and tracking results.

Saliency-Based SAR Target Detection via Convolutional Sparse Feature Enhancement and Bayesian Inference

Traditional synthetic aperture radar (SAR) target detection methods use matched filtered SAR images as input, and the detection performance is restricted due to the high sidelobes and speckle noise of these images. Sparse SAR imaging methods developed in recent years provide the advantages of reducing sidelobes, noise, and clutter. The imaging results obtained with these methods could help improve the SAR target detection performance. In this article, to improve the target detection performance using sparse SAR images as input, we proposed a convolutional sparse feature enhancement method to meet the needs of Bayesian saliency detection. The proposed Bayesian saliency joint target detection method comprised the following three steps: first, to obtain sparse SAR images with continuous contours and fewer holes in the target area, we proposed a convolutional L1 sparse regularization method. Second, a regularization parameter optimization method was derived to quickly obtain optimal regularization parameters for saliency detection. Finally, target detection results were obtained through a superpixel-based Bayesian saliency joint detector. Extensive experiments verified that the proposed method could improve the SAR target detection accuracy in complex backgrounds.

A Radar Waveform Design for Deceiving Noncooperative Bistatic Radars

This letter presents a radar waveform design for deceiving noncooperative bistatic radars (NCBRs). The principle of deceiving the noncooperative bistatic radar is proposed according to some imperfections in the engineering realization of NCBRs whose direct wave parameters are selected from the template library to reconstruct the reference signal. These imperfections are either unavoidable, such as phase asynchrony, or hard to find, such as time errors. For the first time, a radar waveform design method based on joint modulation of the initial phase and the pulse repetition interval (PRI) is proposed to achieve range migration–velocity deception for NCBRs. When our host radar illuminates our key target, the noncooperative bistatic radar will detect our key target. The proposed waveform will mislead the target detection results of the noncooperative bistatic radar in range–time (R–T) maps and range-Doppler (R-D) maps. It can not only be used to disguise a moving target as a stationary point target to avoid moving target detection (MTD) of NCBRs, but also modulate the target echo velocity into the opposite direction of the real motion to prevent our key moving targets from being tracked. Both the simulation data and the measured results show that the deception method proposed in this letter fulfills the requirements of NCBR countermeasures

Ship Detection in SAR Images Based on Multilevel Superpixel Segmentation and Fuzzy Fusion

Superpixel can maintain the boundary of the target and reduce the influence of speckle noise, which has been widely applied to synthetic aperture radar (SAR) image target detection. But the size of the superpixel has a great impact on the performance of superpixel-based SAR target detection algorithms. To solve this problem, we propose a multi-level ship target detection algorithm based on superpixel segmentation. Firstly, the SAR images are segmented in different levels with different superpixel sizes. Different descriptions of the SAR images are obtained in different levels. Secondly, we determine the feature of the superpixels in each level. And in order to enhance the adaptability of the proposed algorithm, we propose an adaptive distance calculation method to select the contrast superpixels in each level. Thirdly, the soft detection results are realized in each level by using the fuzzy C-means (FCM) algorithm. At last, the soft detection results obtained in different levels are fused by a new fusion strategy to achieve the final ship target detection result. The influences caused by different superxiel sizes can be effectively eased by fusion. Experiments in different SAR images have verified the effectiveness of the proposed algorithm in accurately detecting ship targets and insensitivity to the superpixel size.

Multi-target trajectory tracking in multi-frame video images of basketball sports based on deep learning

INTRODUCTION: There is occlusion interference in the multi-target visual tracking process of basketball video images, which leads to poor accuracy of multi-target trajectory tracking. This paper studies the multi-target trajectory tracking method in multi-frame video images of basketball sports based on deep learning. OBJECTIVES: Aiming at the problem of target occlusion in the tracking process and the problem of trajectory tracking anomaly caused by target occlusion, a modified algorithm is proposed. METHODS: The method is divided into two parts: detection and tracking. In the detection part, the YOLOv3 algorithm in deep learning technology is used to detect each target in the video, and the original YOLOv3 backbone network Darknet-53 is replaced by the lightweight backbone network MobileNetV2 to extract the target features. RESULTS: Based on the target detection results, the Kalman filter is used to predict the next position and bounding box size of the target to obtain the target trajectory prediction results according to the current target position, then a hierarchical data association algorithm is designed, and multi-target tracking of the same category is completed based on the target appearance feature similarity and feature similarity. CONCLUSION: The experimental results show that the method can accurately detect the targets in multi-frame video images in basketball sports and obtain high-precision target trajectory tracking results.

Autoencoder-Based Target Detection in Automotive MIMO FMCW Radar System.

In general, a constant false alarm rate algorithm (CFAR) is widely used to automatically detect targets in an automotive frequency-modulated continuous wave (FMCW) radar system. However, if the number of guard cells, the number of training cells, and the probability of false alarm are set improperly in the conventional CFAR algorithm, the target detection performance is severely degraded. Therefore, we propose a method using a convolutional neural network-based autoencoder (AE) to replace the CFAR algorithm in the multiple-input and multiple-output FMCW radar system. In the AE, the entire detection result is compressed at the encoder side, and only significant signal components are recovered on the decoder side. In this work, by changing the number of hidden layers and the number of filters in each layer, the structure of the AE showing a high signal-to-noise ratio in the target detection result is determined. To evaluate the performance of the proposed method, the AE-based target detection result is compared with the target detection results of conventional CFAR algorithms. As a result of calculating the correlation coefficient with the data marked with the actual target position, the proposed AE-based target detection shows the highest similarity with a correlation of 0.73 or higher.