Target Detection Task Research Articles

Data enhancement method based on cyclic generation adversarial network

This study introduces a novel data augmentation technique employing Cycle Generative Adversarial Networks (CycleGAN) to mitigate the challenges posed by the paucity of image datasets in deep learning domains. Through the adept training of a CycleGAN model, this method substantially enriches image datasets, thereby enhancing the efficiency of deep learning models in target detection tasks. Distinct from conventional approaches, our strategy incorporates advanced activation functions, relative discriminators, and residual connections, which collectively foster greater image diversity and mitigate mode collapse, all while maintaining a low computational overhead. Evaluations conducted on diverse datasets, including MNIST, Synthetic Aperture Radar (SAR), and medical blood cell images, demonstrate the method's superior augmentation capabilities compared to traditional Deep Convolutional GAN (DCGAN) techniques, underscoring its efficacy and potential utility in preprocessing for deep learning applications.

Gaze Target Detection by Merging Human Attention and Activity Cues

Despite achieving impressive performance, current methods for detecting gaze targets, which depend on visual saliency and spatial scene geometry, continue to face challenges when it comes to detecting gaze targets within intricate image backgrounds. One of the primary reasons for this lies in the oversight of the intricate connection between human attention and activity cues. In this study, we introduce an innovative approach that amalgamates the visual saliency detection with the body-part & object interaction both guided by the soft gaze attention. This fusion enables precise and dependable detection of gaze targets amidst intricate image backgrounds. Our approach attains state-of-the-art performance on both the Gazefollow benchmark and the GazeVideoAttn benchmark. In comparison to recent methods that rely on intricate 3D reconstruction of a single input image, our approach, which solely leverages 2D image information, still exhibits a substantial lead across all evaluation metrics, positioning it closer to human-level performance. These outcomes underscore the potent effectiveness of our proposed method in the gaze target detection task.

Underwater small target detection based on dynamic convolution and attention mechanism

In ocean observation missions, unmanned autonomous ocean observation platforms play a crucial role, with precise target detection technology serving as a key support for the autonomous operation of unmanned platforms. Among various underwater sensing devices, side-scan sonar (SSS) has become a primary tool for wide-area underwater detection due to its extensive detection range. However, current research on target detection with SSS primarily focuses on large targets such as sunken ships and aircraft, lacking investigations into small targets. In this study, we collected data on underwater small targets using an unmanned boat equipped with SSS and proposed an enhancement method based on the YOLOv7 model for detecting small targets in SSS images. First, to obtain more accurate initial anchor boxes, we replaced the original k-means algorithm with the k-means++ algorithm. Next, we replaced ordinary convolution blocks in the backbone network with Omni-dimensional Dynamic Convolution (ODConv) to enhance the feature extraction capability for small targets. Subsequently, we inserted a Global Attention Mechanism (GAM) into the neck network to focus on global information and extract target features, effectively addressing the issue of sparse target features in SSS images. Finally, we mitigated the harmful gradients produced by low-quality annotated data by adopting Wise-IoU (WIoU) to improve the detection accuracy of small targets in SSS images. Through validation on the test set, the proposed method showed a significant improvement compared to the original YOLOv7, with increases of 5.05% and 2.51% in mAP@0.5 and mAP@0.5: 0.95 indicators, respectively. The proposed method demonstrated excellent performance in detecting small targets in SSS images and can be applied to the detection of underwater mines and small equipment, providing effective support for underwater small target detection tasks.

Target Detection and Segmentation Technology for Zero-shot Learning

Zero-shot learning (ZSL) in the field of computer vision refers to enabling the model to recognize and understand categories that have not been encountered during the training phase. It is particularly critical for object detection and segmentation tasks, because these tasks require the model to have good generalization capabilities to unknown categories. Object detection requires the model to determine the location of the object, while segmentation further requires the precise demarcation of the object's boundaries. In ZSL research, knowledge representation and transfer are core issues. Researchers have tried to use semantic attributes as a knowledge bridge to connect categories seen during the training phase and categories not seen during the testing phase. These attributes may be color, shape, etc., but this method requires accurate attribute annotation, which is often not easy to achieve in practice. Therefore, researchers have begun to explore the use of non-visual information such as knowledge maps and text descriptions to enrich the recognition capabilities of models, but this also introduces the challenge of information integration and alignment. At present, ZSL has made certain progress in target detection and segmentation tasks, but there is still a significant gap compared with traditional supervised learning. This is mainly due to the limited ability of ZSL models to generalize to new categories. To this end, researchers have begun to explore combining ZSL with other technologies, such as generative adversarial networks (GANs) and reinforcement learning, to enhance the model's detection and segmentation capabilities for new categories. Future research needs to focus on several aspects. The first is how to design a more effective knowledge representation and transfer mechanism so that the model can better utilize existing knowledge. The second step is to develop new algorithms to improve the performance of ZSL in complex environments. In addition, research should focus on how to reduce the dependence on computing resources so that the ZSL method can run effectively in resource-limited environments. In summary, the research on target detection and segmentation technology of zero-shot learning is a cutting-edge topic in the field of computer vision. Despite the challenges, with the deepening of research, we expect these technologies to contribute to improving the generalization ability and intelligence level of computer vision systems.

Underwater Rescue Target Detection Based on Acoustic Images.

In order to effectively respond to floods and water emergencies that result in the drowning of missing persons, timely and effective search and rescue is a very critical step in underwater rescue. Due to the complex underwater environment and low visibility, unmanned underwater vehicles (UUVs) with sonar are more efficient than traditional manual search and rescue methods to conduct active searches using deep learning algorithms. In this paper, we constructed a sound-based rescue target dataset that encompasses both the source and target domains using deep transfer learning techniques. For the underwater acoustic rescue target detection of small targets, which lack image feature accuracy, this paper proposes a two-branch convolution module and improves the YOLOv5s algorithm model to design an acoustic rescue small target detection algorithm model. For an underwater rescue target dataset based on acoustic images with a small sample acoustic dataset, a direct fine-tuning using optical image pre-training lacks cross-domain adaptability due to the different statistical properties of optical and acoustic images. This paper therefore proposes a heterogeneous information hierarchical migration learning method. For the false detection of acoustic rescue targets in a complex underwater background, the network layer is frozen during the hierarchical migration of heterogeneous information to improve the detection accuracy. In addition, in order to be more applicable to the embedded devices carried by underwater UAVs, an underwater acoustic rescue target detection algorithm based on ShuffleNetv2 is proposed to improve the two-branch convolutional module and the backbone network of YOLOv5s algorithm, and to create a lightweight model based on hierarchical migration of heterogeneous information. Through extensive comparative experiments conducted on various acoustic images, we have thoroughly validated the feasibility and effectiveness of our method. Our approach has demonstrated state-of-the-art performance in underwater search and rescue target detection tasks.

A novel low light object detection method based on the YOLOv5 fusion feature enhancement

Low-light object detection is an important research area in computer vision, but it is also a difficult issue. This research offers a low-light target detection network, NLE-YOLO, based on YOLOV5, to address the issues of insufficient illumination and noise interference experienced by target detection tasks in low-light environments. The network initially preprocesses the input image with an improvement technique before suppressing high-frequency noise and enhancing essential information with C2fLEFEM, a unique feature extraction module. We also created a multi-scale feature extraction module, AMC2fLEFEM, and an attention mechanism receptive field module, AMRFB, which are utilized to extract features of multiple scales and enhance the receptive field. The C2fLEFEM module, in particular, merges the LEF and FEM modules on top of the C2f module. The LEF module employs a low-frequency filter to remove high-frequency noise; the FEM module employs dual inputs to fuse low-frequency enhanced and original features; and the C2f module employs a gradient retention method to minimize information loss. The AMC2fLEFEM module combines the SimAM attention mechanism and uses the pixel relationship to obtain features of different receptive fields, adapt to brightness changes, capture the difference between the target and the background, improve the network's feature extraction capability, and effectively reduce the impact of noise. The AMRFB module employs atrous convolution to enlarge the receptive field, maintain global information, and adjust to targets of various scales. Finally, for low-light settings, we replaced the original YOLOv5 detection head with a decoupled head. The Exdark dataset experiments show that our method outperforms previous methods in terms of detection accuracy and performance.

Deep learning based multi-target detection for roads

The vehicle target detection algorithm based on deep learning has gradually become a research hotspot in this field. In recent years, with the significant breakthrough of deep learning in the field of target recognition, the vehicle target detection algorithm based on deep learning has gradually become a research hotspot in this field. For the task of vehicle target detection, this paper first briefly introduces the process of traditional target detection algorithms and some optimization methods. It summarizes the development process of YOLO, the current mainstream one-stage vehicle target detection algorithm, and the process of Faster R-CNN, the second-stage vehicle target detection algorithm, and its improvement. Then the characteristics of several types of representative convolutional neural network algorithms are analyzed in chronological development order. Finally, it looks forward to t he future research direction of vehicle target detection algorithms, and also provides new ideas for the optimization of the subsequent vehicle target detection algorithms, which have good engineering application value. Provides algorithmic support for the underlying logic of autonomous driving.

A Deep Learning Approach of Intrusion Detection and Tracking with UAV-Based 360° Camera and 3-Axis Gimbal

Intrusion detection is often used in scenarios such as airports and essential facilities. Based on UAVs equipped with optical payloads, intrusion detection from an aerial perspective can be realized. However, due to the limited field of view of the camera, it is difficult to achieve large-scale continuous tracking of intrusion targets. In this study, we proposed an intrusion target detection and tracking method based on the fusion of a 360° panoramic camera and a 3-axis gimbal, and designed a detection model covering five types of intrusion targets. During the research process, the multi-rotor UAV platform was built. Then, based on a field flight test, 3043 flight images taken by a 360° panoramic camera and a 3-axis gimbal in various environments were collected, and an intrusion data set was produced. Subsequently, considering the applicability of the YOLO model in intrusion target detection, this paper proposes an improved YOLOv5s-360ID model based on the original YOLOv5-s model. This model improved and optimized the anchor box of the YOLOv5-s model according to the characteristics of the intrusion target. It used the K-Means++ clustering algorithm to regain the anchor box that matches the small target detection task. It also introduced the EIoU loss function to replace the original CIoU loss function. The target bounding box regression loss function made the intrusion target detection model more efficient while ensuring high detection accuracy. The performance of the UAV platform was assessed using the detection model to complete the test flight verification in an actual scene. The experimental results showed that the mean average precision (mAP) of the YOLOv5s-360ID was 75.2%, which is better than the original YOLOv5-s model of 72.4%, and the real-time detection frame rate of the intrusion detection was 31 FPS, which validated the real-time performance of the detection model. The gimbal tracking control algorithm for intrusion targets is also validated. The experimental results demonstrate that the system can enhance intrusion targets’ detection and tracking range.

The Internet of Things Drives Smart City Management

In the context of current smart city development, the efficiency of urban management has become crucial. Target detection technology plays a vital role in addressing the complexity of urban environments. The authors propose a new method called YOLOv8_k, employing transfer learning as its foundation. This method leverages pre-trained model parameters from related tasks to incorporate prior knowledge into the target detection model, adapting better to the complexity of smart city management scenarios. Experimental results demonstrate the outstanding performance of YOLOv8_k. In specific experimental results, YOLOv8_k shows significant improvements across multiple evaluation metrics. The average precision in target detection tasks experiences a notable increase. Furthermore, in large-scale urban datasets, compared to traditional methods, YOLOv8_k exhibits higher responsiveness in handling large volumes of real-time data, further demonstrating its superiority in practical applications.

Morphine exposure modulates dimensional bias and set formation in anthropoids.

Humans demonstrate significant behavioural advantages with particular perceptual dimensions (such as colour or shape) and when the relevant dimension is repeated in consecutive trials. These dimension-related behavioural modulations are significantly altered in neuropsychological and addiction disorders; however, their underlying mechanisms remain unclear. Here, we studied whether these behavioural modulations exist in other trichromatic primate species and whether repeated exposure to opioids influences them. In a target detection task where the target-defining dimension (colour or shape) changed trial by trial, humans exhibited shorter response time (RT) and smaller event-related electrodermal activity with colour dimension; however, macaque monkeys had shorter RT with shape dimension. Although the dimensional biases were in the opposite directions, both species were faster when the relevant dimension was repeated, compared with conditions when it changed, across consecutive trials. These indicate that both species formed dimensional sets and that resulted in a significant 'switch cost'. Scheduled and repeated exposures to morphine, which is analogous to its clinical and recreational use, significantly augmented the dimensional bias in monkeys and also changed the switch cost depending on the relevant dimension. These cognitive effects occurred when monkeys were in abstinence periods (not under acute morphine effects) but expressing significant morphine-induced conditioned place preference. These findings indicate that significant dimensional biases and set formation are evolutionarily preserved in humans' and monkeys' cognition and that repeated exposure to morphine interacts with their manifestation. Shared neural mechanisms might be involved in the long-lasting effects of morphine and expression of dimensional biases and set formation in anthropoids.

Multisensory integration deficits in Schizophrenia and Autism evidenced in behaviour but not event related potentials

The process of integrating information from different sensory channels, known as multisensory integration (MSI) was assessed in two disorders, Autism Spectrum Disorder (ASD) and Schizophrenia (SCZ). 32 healthy controls (HC), 35 SCZ patients, and 23 ASD patients performed an audiovisual (AV) synchronous target detection task while reaction time (RT) and scalp recorded electrophysiological (EEG) activity were measured. MSI in the AV condition resulted in faster and less variable RTs compared to the unimodal conditions. Using our novel bootstrap method, MSI gain was observed in 78 % of HC, 26 % of ASD, and 48 % of SCZ patients. At the neural level, MSI in the AV condition resulted in larger amplitude of sensory evoked responses and cognitive P3 response compared to the corresponding unimodal conditions. These neural effects of MSI were not related to the behavioural MSI gain identified at the individual level and could not explain the deficits in behavioural MSI of patient groups. In conclusion, a robust MSI gain deficit in RT was observed in both patient groups that was not reflected in early perceptual and cognitive electro-cortical responses, suggesting that behavioural MSI deficits in ASD and SCZ may arise at late processing stages such as response selection.

PI-YOLO: dynamic sparse attention and lightweight convolutional based YOLO for vessel detection in pathological images.

Vessel density within tumor tissues strongly correlates with tumor proliferation and serves as a critical marker for tumor grading. Recognition of vessel density by pathologists is subject to a strong inter-rater bias, thus limiting its prognostic value. There are many challenges in the task of object detection in pathological images, including complex image backgrounds, dense distribution of small targets, and insignificant differences between the features of the target to be detected and the image background. To address these problems and thus help physicians quantify blood vessels in pathology images, we propose Pathological Images-YOLO (PI-YOLO), an enhanced detection network based on YOLOv7. PI-YOLO incorporates the BiFormer attention mechanism, enhancing global feature extraction and accelerating processing for regions with subtle differences. Additionally, it introduces the CARAFE upsampling module, which optimizes feature utilization and information retention for small targets. Furthermore, the GSConv module improves the ELAN module, reducing model parameters and enhancing inference speed while preserving detection accuracy. Experimental results show that our proposed PI-YOLO network has higher detection accuracy compared to Faster-RCNN, SSD, RetinaNet, YOLOv5 network, and the latest YOLOv7 network, with a mAP value of 87.48%, which is 2.83% higher than the original model. We also validated the performance of this network on the ICPR 2012 mitotic dataset with an F1 value of 0.8678, outperforming other methods, demonstrating the advantages of our network in the task of target detection in complex pathology images.

Cognitive Profiles Stratified by Education Using Montreal Cognitive Assessment in Parkinson's Disease Patients with Freezing of Gait.

Parkinson's disease (PD) patients with freezing of gait (FOG) may present with complex and heterogeneous cognitive profiles. Owing to limited access to comprehensive neuropsychological battery in ordinary clinical practice, the Montreal Cognitive Assessment (MoCA) is likely to be easily available cognitive data for comparisons among studies. This study aims to explore the cognitive profiles stratified by education using MoCA in PD patients with FOG. PD patients with FOG (FOG+, n = 52) and without FOG (FOG-, n = 71) were included in our study. MoCA items were categorized into five subsections (attention/working memory, executive function, episodic memory, language, and visuospatial function) referring to previously published criteria. Cognitive assessments were compared based on five subsections between groups stratified by three education levels (0-6 years, 7-12 years, and >12 years). The association of cognitive measurements with FOG were analyzed using binary logistic regression models with adjustment for variables. The total scores and subscores of each subsection of MoCA were similar between two groups of each education level. Further detailed analysis showed that a composite measure labeled "Attention/working memory-Composite" (abbreviated to Attention-C), consisting of the scores of four items (target detection task, serial sevens, digit forward and backward, and sentence repetition), were lower significantly in FOG+ group compared with FOG- group in patients with education year ≤6 years. The significant association of Attention-C with FOG held true when controlling for disease duration, but not for H-Y stage, MDS-UPDRS III, HAMA, and HAMD. Overall, our findings gave a hint that Attention-C derived from MoCA might be a potential factor associated with FOG in PD patients with lower education level (education year ≤ 6 years), which will need to be validated in future studies.

Seg2Sonar: A Full-Class Sample Synthesis Method Applied to Underwater Sonar Image Target Detection, Recognition, and Segmentation Tasks

Seg2Sonar: A Full-Class Sample Synthesis Method Applied to Underwater Sonar Image Target Detection, Recognition, and Segmentation Tasks

Target Detection in Remote Sensing Images Based on Recognition Algorithm

Abstract Aiming at the problem of low target detection accuracy caused by the close arrangement of targets, complex feature information, and numerous small targets in remote sensing images, this paper proposes a target detection algorithm based on the improved Yolov5 algorithm for remote sensing images. Firstly, this paper designs a remote sensing image target detection algorithm C²-YOLO based on multi-level feature fusion. Combined with the attention mechanism module to focus on the spatial location information of the target, which improves the extraction effect of the features of the target of interest. The network uses the CARAFE upsampling operator with a larger sensing field to better utilize the surrounding information. The proposal is to incorporate a predictive header hl that is generated from a low-level, high-resolution feature map to improve the recognition of tiny objects. The problem of large target scales in remote sensing images and poor detection of small targets has been improved. Angular loss is also added to the loss function to improve the detection of rotating targets. Finally, the accuracy comparison and experimental effect visualization are carried out on the dataset, and the experimental results show that the improvement work in this paper achieves better results no matter comparing the original YOLOv5 detection algorithm or other types of detection algorithms. Specifically, the accuracy of C²-YOLO on the NWPU dataset 1-shot recognition task is 78.45%, which is much higher than that of other detection algorithms, and is able to reach a superior performance in the remote sensing image target detection task.

3D Target Detection Algorithm of Laser Point Cloud Based on Artificial Intelligence

Traditional target detection methods based on manual features have limitations, and it is difficult to adapt to complex scenes and various types of targets. Recently, three-dimensional target detection tasks have achieved good performance using artificial intelligence technology that is based on deep learning methods. Based on this, this paper presents a three-dimensional laser point cloud target detection algorithm based on deep learning. First, the point cloud segmentation network is designed for data semantic segmentation of the original point cloud, and the point cloud is categorized in semantic regions. Then, a point cloud region proposal network to generate region proposals according to the categorization results. Finally, the target recognition network of the point cloud is designed to achieve the detection of three-dimensional objects, specifically by conducting proposal classification and position regression. The entire algorithm integrates key modules such as point cloud segmentation, area proposal, and target recognition end-to-end, and fully excavates the geometric characteristics and semantic information of point cloud data. Experimental verification is carried out on the public benchmark data set, and the results show that the proposed algorithm has achieved state-of-the-art performance in the three-dimensional target detection task, and the detection accuracy and recall rate have reached a high level.

Willed Attentional Selection of Visual Features: An EEG Study.

Visual selective attention studies generally tend to apply cuing paradigms to instructively direct observers' attention to certain locations, features or objects. However, in real situations, attention in humans often flows spontaneously without any specific instructions. Recently, a concept named "willed attention" was raised in visuospatial attention, in which participants are free to make volitional attention decisions. Several ERP components during willed attention were found, along with a perspective that ongoing alpha activity may bias the subsequent attentional choice. However, it remains unclear whether similar neural mechanisms exist in feature- or object-based willed attention. Here, we included choice cues and instruct cues in a feature-based selective attention paradigm, allowing participants to freely choose or to be instructed to attend a color for the subsequent target detection task. Pre-cue ongoing alpha oscillations, cue-evoked potentials and target-related steady-state visual evoked potentials (SSVEPs) were simultaneously measured as markers of attentional processing. As expected, SSVEP responses were similarly modulated by attention between choice and instruct cue trials. Similar to the case of spatial attention, a willed-attention component (Willed Attention Component, WAC) was isolated during the cue-related choice period by comparing choice and instruct cues. However, pre-cue ongoing alpha oscillations did not predict the color choice (yellow vs blue), as indicated by the chance level decoding accuracy (50%). Overall, our results revealed both similarities and differences between spatial and feature-based willed attention, and thus extended the understanding toward the neural mechanisms of volitional attention.

Spectral uncertainty analysis of grassland and its camouflage materials based on land-based hyperspectral images

Abstract Spectral uncertainty is one of the most prominent spectral characteristics of hyperspectral images. Compared to the process of remote sensing hyperspectral imaging, hyperspectral imaging under land-based imaging conditions has the characteristics of variable detection directions, random imaging times, and complex environmental conditions, resulting in increased spectral uncertainty of targets in land-based hyperspectral images. The spectral uncertainty of the target mainly refers to the phenomenon of “Same spectral reflectance but different objects” and “Same object but different spectral reflectance” which poses significant difficulties for subsequent hyperspectral image target detection and recognition. In order to analyze the spectral uncertainty of hyperspectral images in land-based applications and address the issue of spectral uncertainty in similar targets, a spectral uncertainty evaluation index based on standard deviation vector was proposed. For the overall spectral separability between different types of targets, a quantitative index based on Jaccard Distance (JD-SSI) is proposed to measure the spectral separability of different kinds of targets. The experiment focused on grassland and its four typical camouflage materials, analyzing the spectral intra class differences and inter class separability of each target with grassland. It is a fundamental work for studying the spectral characteristics of land-based hyperspectral images, providing a new approach for subsequent spectral band extraction, hyperspectral image classification, and target detection tasks.

Object Recognition and Grasping for Collaborative Robots Based on Vision.

This study introduces a parallel YOLO-GG deep learning network for collaborative robot target recognition and grasping to enhance the efficiency and precision of visual classification and grasping for collaborative robots. First, the paper outlines the target classification and detection task, the grasping system of the robotic arm, and the dataset preprocessing method. The real-time recognition and grasping network can identify a diverse spectrum of unidentified objects and determine the target type and appropriate capture box. Secondly, we propose a parallel YOLO-GG deep vision network based on YOLO and GG-CNN. Thirdly, the YOLOv3 network, pre-trained with the COCO dataset, identifies the object category and position, while the GG-CNN network, trained using the Cornell Grasping dataset, predicts the grasping pose and scale. This study presents the processes for generating a target's grasping frame and recognition type using GG-CNN and YOLO networks, respectively. This completes the investigation of parallel networks for target recognition and grasping in collaborative robots. Finally, the experimental results are evaluated on the self-constructed NEU-COCO dataset for target recognition and positional grasping. The speed of detection has improved by 14.1%, with an accuracy of 94%. This accuracy is 4.0% greater than that of YOLOv3. Experimental proof was obtained through a robot grasping actual objects.

Action does not drive visual biases in peri-tool space.

Observers experience visual biases in the area around handheld tools. These biases may occur when active use leads an observer to incorporate a tool into the body schema. However, the visual salience of a handheld tool may instead create an attentional prioritization that is not reliant on body-based representations. We investigated these competing explanations of near-tool visual biases in two experiments during which participants performed a target detection task. Targets could appear near or far from a tool positioned next to a display. In Experiment 1, participants showed facilitation in detecting targets that appeared near a simple handheld rake tool regardless of whether they first used the rake to retrieve objects, but participants who only viewed the tool without holding it were no faster to detect targets appearing near the rake than targets that appeared on the opposite side of the display. In a second experiment, participants who held a novel magnetic tool again showed a near-tool bias even when they refrained from using the tool. Taken together, these results suggest active use is unnecessary, but visual salience is not sufficient, to introduce visual biases in peri-tool space.