Target In Complex Environment Research Articles

A ship detection model with progressive feature fusion and cross-spatial learning attention mechanism for optical remote sensing images

Abstract Using remote sensing images to detect ships is vital for port management, maritime transportation, and security. Challenges such as false detection and omission arise in ship target detection in optical remote sensing images due to the complexity of the background and the diversity of target scales. To address these issues, this paper proposes a novel model called MBE-YOLO. Firstly, the multiscale input spatial pyramid pooling-fast structure is designed to effectively extract more feature information by efficiently integrating the features from different stages of the backbone network. Secondly, the backbone to neck structure is designed with a progressive architecture to mitigate semantic differences between non-adjacent layers in the feature delivery process, thereby significantly reducing the risk of information loss. Finally, we introduce the efficient multi-scale attention attention mechanism, which establishes short and long dependencies through multi-scale parallel subnetworks. This enhances the ability to detect targets in complex environments at various scales. MBE-YOLO is applied to the HRSC2016 and HiresShipDetection datasets. Comparison experiments with current mainstream and state-of-the-art models demonstrate its effectiveness in addressing errors and omissions due to scene complexity and scale variations in remote sensing ship detection, with a parameter size of only 3.24 M.

An efficient transformer network for detecting multi-scale chicken in complex free-range farming environments via improved RT-DETR

Accurate detection and localization of chicken targets in complex environments are the foundation of intelligent free-range chicken farming. However, commercial free-range chicken farming poses several challenges to detection methods, including complex and variable backgrounds, multi-scale targets, aggregated occlusion and changes in the posture of chicken. While there has been significant research on object detection algorithms based on convolutional neural networks, these algorithms have limited effectiveness in detecting small targets and generalizing to new scenes. Therefore, this study proposes a highly accurate and strongly generalizable chicken object detection model called Efficient Multi-scale Chicken DETR (EMSC-DETR), which is based on an improved Real-Time DEtection TRansformer (RT-DETR). To address the issue of easily losing small target features, a new efficient transformer module called space-to-depth transformer module (SDTM) is introduced. SDTM includes space-to-depth (SPD) and BiFormer modules, which facilitate deep interaction between local and global features, and significantly improve the computational efficiency of the transformer. Additionally, to overcome the detection and differentiation difficulties caused by chicken aggregation occlusion, the transformer encoder of EMSC-DETR incorporates a contextual transformer (CoT). CoT utilizes rich contextual information among the nearest neighbors to enhance the feature representation of high-level features, enabling more accurate localization of overlapped chicken targets. To evaluate the proposed model in complex environments, 14 scene data were collected from two fields and divided into training, validation, testing sets and three independent testing sets with unknown scenes. Experimental results show that the proposed EMSC-DETR obtains the best detection performance in the testing set, with an AP50 of 98.6%, surpassing other state-of-the-art models of similar size. In the three independent testing sets, the proposed model shows improvements of 8.2%, 9.2% and 28.3% in the AP50 compared to the original RT-DETR, respectively. Moreover, the model exhibits superior generalization ability for unknown scenes compared to other state-of-the-art models. Robustness and fine-tuning experiments further confirm the reliability and application potential of EMSC-DETR in detecting free-range chickens, which is crucial for complex commercial farming. This study is expected to provide references and new ideas for precision livestock farming.

A lightweight fire detection algorithm for small targets based on YOLOv5s

In response to the current challenges fire detection algorithms encounter, including low detection accuracy and limited recognition rates for small fire targets in complex environments, we present a lightweight fire detection algorithm based on an improved YOLOv5s. The introduction of the CoT (Contextual Transformer) structure into the backbone neural network, along with the creation of the novel CSP1_CoT (Cross stage partial 1_contextual transformer) module, has effectively reduced the model’s parameter count while simultaneously enhancing the feature extraction and fusion capabilities of the backbone network; The network’s Neck architecture has been extended by introducing a dedicated detection layer tailored for small targets and incorporating the SE (Squeeze-and-Excitation) attention mechanism. This augmentation, while minimizing parameter proliferation, has significantly bolstered the interaction of multi-feature information, resulting in an enhanced small target detection capability; The substitution of the original loss function with the Focal-EIoU (Focal-Efficient IoU) loss function has yielded a further improvement in the model’s convergence speed and precision; The experimental results indicate that the modified model achieves an mAP@.5 of 96% and an accuracy of 94.8%, marking improvements of 8.8% and 8.9%, respectively, over the original model. Furthermore, the model’s parameter count has been reduced by 1.1%, resulting in a compact model size of only 14.6MB. Additionally, the detection speed has reached 85 FPS (Frames Per Second), thus satisfying real-time detection requirements. This enhancement in precision and accuracy, while simultaneously meeting real-time and lightweight constraints, effectively caters to the demands of fire detection.

Multi‐target detection and tracking of shallow marine organisms based on improved YOLO v5 and DeepSORT

AbstractIn order to solve the related problems of detection and tracking of shallow marine organisms, this paper designs a YOLO v5 multi‐target detection and tracking algorithm with attention mechanism. When working underwater, the authors usually encounter many difficulties. Different luminosity and complex coral background usually affect the detection of marine organisms. At the same time, the unrestricted movement of marine organisms, the ability to hide behind rocks and algae, and their mutual occlusion while swimming pose additional challenges to this task. Considering the characteristics of shallow marine organisms activity environment, the attention mechanism is added to the feature extraction network of YOLO v5 to reduce redundant information and improve the detection accuracy of shallow marine organism targets in complex environment. The improved algorithm improves the average detection accuracy of marine organisms target detection by 3.2%. Aiming at the problem of shallow marine organisms target tracking, a shallow marine organisms multi‐target tracking algorithm based on improved Deep Simple Online And Realtime Tracking (SORT) is designed. The improved YOLO v5 algorithm is used to replace Faster R‐CNN (Faster Region‐Convolutional Neural Networks) as the detector of DeepSORT tracking algorithm, and the cascade matching strategy is adopted to solve the problem that the target cannot be tracked continuously when it is occluded for a long time. The experimental results show that the shallow marine organisms multi‐target tracking algorithm based on improved DeepSORT reduces the number of id transformation of marine biological target tracking in shallow sea environment, and improves the accuracy of shallow marine organisms multi‐target tracking.

Design and Algorithm Integration of High-Precision Adaptive Underwater Detection System Based on MEMS Vector Hydrophone.

Real-time DOA (direction of arrival) estimation of surface or underwater targets is of great significance to the research of marine environment and national security protection. When conducting real-time DOA estimation of underwater targets, it can be difficult to extract the prior characteristics of noise due to the complexity and variability of the marine environment. Therefore, the accuracy of target orientation in the absence of a known noise is significantly reduced, thereby presenting an additional challenge for the DOA estimation of the marine targets in real-time. Aiming at the problem of real-time DOA estimation of acoustic targets in complex environments, this paper applies the MEMS vector hydrophone with a small size and high sensitivity to sense the conditions of the ocean environment and change the structural parameters in the adaptive adjustments system itself to obtain the desired target signal, proposes a signal processing method when the prior characteristics of noise are unknown. Theoretical analysis and experimental verification show that the method can achieve accurate real-time DOA estimation of the target, achieve an error within 3.1° under the SNR (signal-to-noise ratio) of the X channel of -17 dB, and maintain a stable value when the SNR continues to decrease. The results show that this method has a very broad application prospect in the field of ocean monitoring.

Detection of Military Targets on Ground and Sea by UAVs with Low-Altitude Oblique Perspective

Small-scale low-altitude unmanned aerial vehicles (UAVs) equipped with perception capability for military targets will become increasingly essential for strategic reconnaissance and stationary patrols in the future. To respond to challenges such as complex terrain and weather variations, as well as the deception and camouflage of military targets, this paper proposes a hybrid detection model that combines Convolutional Neural Network (CNN) and Transformer architecture in a decoupled manner. The proposed detector consists of the C-branch and the T-branch. In the C-branch, Multi-gradient Path Network (MgpNet) is introduced, inspired by the multi-gradient flow strategy, excelling in capturing the local feature information of an image. In the T-branch, RPFormer, a Region–Pixel two-stage attention mechanism, is proposed to aggregate the global feature information of the whole image. A feature fusion strategy is proposed to merge the feature layers of the two branches, further improving the detection accuracy. Furthermore, to better simulate real UAVs’ reconnaissance environments, we construct a dataset of military targets in complex environments captured from an oblique perspective to evaluate the proposed detector. In ablation experiments, different fusion methods are validated, and the results demonstrate the effectiveness of the proposed fusion strategy. In comparative experiments, the proposed detector outperforms most advanced general detectors.

Research on Small Target Detection Method for Industrial Safety Helmets Based on Improved YOLOv8

Industrial safety helmets are crucial personal protective gear but detecting them as small targets in complex environments is challenging. This work proposes enhancements to the YOLOv8 object detection framework, specifically incorporating a spatial-to-depth (SPD) convolution module and a large selective kernel network (LSKNet). SPD-Conv combines spatial-to- depth layers and non-strided convolutions to retain fine-grained information when downscaling feature maps, while LSKNet introduces dynamic spatial selection and attention for refined context modeling. Our customized model is trained on a dataset of construction hardhat images captured via drones. Quantitative results showcase higher precision and recall over baseline YOLOv8, surpassing competing YOLOv5 versions. An optimized final model outcomes demonstrate accuracy exceeding 90% validation in mAP metric after 200 training rounds. By tackling limitations posed by small, obscured industrial safety gears, this enhanced real-time detection approach provides indispensable technological support for bolstering workplace hazard identification and prevention.

Large-Scale, Mechanically Robust, Solvent-Resistant, and Antioxidant MXene-Based Composites for Reliable Long-Term Infrared Stealth.

MXene-based thermal camouflage materials have gained increasing attention due to their low emissivity, however, the poor anti-oxidation restricts their potential applications under complex environments. Various modification methods and strategies, e.g., the addition of antioxidant molecules and fillers have been developed to overcome this, but the realization of long-term, reliable thermal camouflage using MXene network (coating) with excellent comprehensive performance remains a great challenge. Here, a MXene-based hybrid network comodified with hyaluronic acid (HA) and hyperbranched polysiloxane (HSi) molecules is designed and fabricated. Notably, the presence of appreciated HA molecules restricts the oxidation of MXene sheets without altering infrared stealth performance, superior to other water-soluble polymers; while the HSi molecules can act as efficient cross-linking agents to generate strong interactions between MXene sheets and HA molecules. The optimized MXene/HA/HSi composites exhibit excellent mechanical flexibility (folded into crane structure), good water/solvent resistance, and long-term stable thermal camouflage capability (with low infrared emissivity of ≈0.29). The long-term thermal camouflage reliability (≈8 months) under various outdoor weathers and the scalable coating capability of the MXene-coated textile enable them to disguise the IR signal of various targets in complex environments, indicating the great promise of achieved material for thermal camouflage, IR stealth, and counter surveillance.

Inverse Firefly-Based Search Algorithms for Multi-Target Search Problem

Efficiently searching for multiple targets in complex environments with limited perception and computational capabilities is challenging for multiple robots, which can coordinate their actions indirectly through their environment. In this context, swarm intelligence has been a source of inspiration for addressing multi-target search problems in the literature. So far, several algorithms have been proposed for solving such a problem, and in this study, we propose two novel multi-target search algorithms inspired by the Firefly algorithm. Unlike the conventional Firefly algorithm, where light is an attractor, light represents a negative effect in our proposed algorithms. Upon discovering targets, robots emit light to repel other robots from that region. This repulsive behavior is intended to achieve several objectives: (1) partitioning the search space among different robots, (2) expanding the search region by avoiding areas already explored, and (3) preventing congestion among robots. The proposed algorithms, named Global Lawnmower Firefly Algorithm (GLFA) and Random Bounce Firefly Algorithm (RBFA), integrate inverse light-based behavior with two random walks: random bounce and global lawnmower. These algorithms were implemented and evaluated using the ArGOS simulator, demonstrating promising performance compared to existing approaches.

Research on Multi-Hole Localization Tracking Based on a Combination of Machine Vision and Deep Learning

In the process of industrial production, manual assembly of workpieces exists with low efficiency and high intensity, and some of the assembly process of the human body has a certain degree of danger. At the same time, traditional machine learning algorithms are difficult to adapt to the complexity of the current industrial field environment; the change in the environment will greatly affect the accuracy of the robot’s work. Therefore, this paper proposes a method based on the combination of machine vision and the YOLOv5 deep learning model to obtain the disk porous localization information, after coordinate mapping by the ROS communication control robotic arm work, in order to improve the anti-interference ability of the environment and work efficiency but also reduce the danger to the human body. The system utilizes a camera to collect real-time images of targets in complex environments and, then, trains and processes them for recognition such that coordinate localization information can be obtained. This information is converted into coordinates under the robot coordinate system through hand–eye calibration, and the robot is then controlled to complete multi-hole localization and tracking by means of communication between the upper and lower computers. The results show that there is a high accuracy in the training and testing of the target object, and the control accuracy of the robotic arm is also relatively high. The method has strong anti-interference to the complex environment of industry and exhibits a certain feasibility and effectiveness. It lays a foundation for achieving the automated installation of docking disk workpieces in industrial production and also provides a more favorable choice for the production and installation of the process of screw positioning needs.

PE-Transformer: Path enhanced transformer for improving underwater object detection

Traditional object detection methods cannot effectively identify underwater objects with complex backgrounds, and it is difficult to fully obtain the details of small-scale underwater targets, resulting in poor detection performance. We propose a path-augmented Transformer detection framework to address these limitations to explore the semantic details of small-scale underwater targets in complex environments. On one hand, an embedded local path detection information scheme is devised to facilitate the interaction between high-level and low-level features, thereby enhancing the semantic representation of distinctive features of small-scale underwater targets. Rich dependency relationships are established between the acquired high-level and low-level features within the CSWin-Transformer framework, thus fortifying the semantic representation during the encoding phase. Furthermore, a individualized loss function is employed to optimize and fine-tune features at various hierarchical levels. On the other hand, a detection module with flexible and adaptive point representation that is different from conventional square detection methods is designed. This module covers the underwater target from any direction, and the salient point samples in classification localization and feature selection between points realize the feature selection improves the detection accuracy of underwater objects simultaneously. We designed a new weighted loss function to encourage the network to converge better. Experimental results on open-source underwater and remote sensing images of UTDAC, RUOD, and ADios show that the proposed method outperforms other underwater object detection methods in terms of precision(P), recall(R), comprehensive evaluation index of F1-score and FPS(frames per second).

A Fourier neuromorphic visual system based on InGaZnO synaptic transistor

The hierarchical structure of the biological visual system enables multilevel features of sensory stimuli to be pre-extracted before being transmitted to the nerve center, rendering the remarkable ability to perceive, filter, categorize, and identify targets in complex environments. However, it is a challenge to resemble such extraction capability with respect to spatial features in a neuromorphic visual system. In this Letter, we propose an indium-gallium-zinc-oxide synaptic transistor-based Fourier neuromorphic visual system for image style classifying. The images are transformed into the frequency domain through an optic Fourier system, greatly reducing energy and time dissipation in comparison with numerical computation. Then, the transformed information is coded into spike trains, which are nonlinearly filtered by synaptic transistors. The energy consumption for this filtering process is estimated to be ∼1.28 nJ/pixel. The features of drawing style could be enhanced through the filtering process, which facilitates the followed pattern recognition. The recognition accuracy in classifying stylized images is significantly improved to 92% through such Fourier transform and filtering process. This work would be of profound implications for advancing neuromorphic visual system with Fourier optics enhanced feature extraction capabilities.

A smartphone-controlled portable multiplexed photoelectrochemical sensor based on dual UV intelligent response system-assisted signal resolution strategy

Portable multiplexed photoelectrochemical (PEC) sensor is essential for on-site detection of multiple targets in complex environment. However, the evolution of portable multiplexed PEC sensor is still constrained by specialized instruments and complex multi-interface modification steps, etc. In this work, we design a UV-assisted multiple signals resolution strategy and construct a smartphone-controlled portable multiplexed PEC sensor. Specifically, following the dual-target biorecognition, UV light triggers the cleavage of photo-responsive DNA so that the dual DNA signal labels can be separated. When the signal label (first target) attaches to the azobenzene-covalently bound DNA (Abz-DNA) and triggers HCR on the electrode surface, UV light illumination induces the structure change of azobenzene, resulting in the detachment of Abz-DNA/HCR complex from the electrode surface. After reincorporation of fresh Abz-DNA, the reconstituted photoelectrode can be reused for the second target analysis. The feasibility of the sensor is validated through the simultaneous detection of two co-existing mycotoxins in corn. Notably, the UV-meditated signal discrimination strategy and smartphone-displayed multi-photocurrent readout enable the portability of the PEC sensor, making it possible for in-situ monitoring of environmental safety and food quality.

Research on a vehicle and pedestrian detection algorithm based on improved attention and feature fusion.

With the widespread integration of deep learning in intelligent transportation and various industrial sectors, target detection technology is gradually becoming one of the key research areas. Accurately detecting road vehicles and pedestrians is of great significance for the development of autonomous driving technology. Road object detection faces problems such as complex backgrounds, significant scale changes, and occlusion. To accurately identify traffic targets in complex environments, this paper proposes a road target detection algorithm based on the enhanced YOLOv5s. This algorithm introduces the weighted enhanced polarization self attention (WEPSA) self-attention mechanism, which uses spatial attention and channel attention to strengthen the important features extracted by the feature extraction network and suppress insignificant background information. In the neck network, we designed a weighted feature fusion network (CBiFPN) to enhance neck feature representation and enrich semantic information. This strategic feature fusion not only boosts the algorithm's adaptability to intricate scenes, but also contributes to its robust performance. Then, the bounding box regression loss function uses EIoU to accelerate model convergence and reduce losses. Finally, a large number of experiments have shown that the improved YOLOv5s algorithm achieves mAP@0.5 scores of 92.8% and 53.5% on the open-source datasets KITTI and Cityscapes. On the self-built dataset, the mAP@0.5 reaches 88.7%, which is 1.7%, 3.8%, and 3.3% higher than YOLOv5s, respectively, ensuring real-time performance while improving detection accuracy. In addition, compared to the latest YOLOv7 and YOLOv8, the improved YOLOv5 shows good overall performance on the open-source datasets.

Polarization- and Gate-Tunable Optoelectronic Reverse in 2D Semimetal/Semiconductor Photovoltaic Heterostructure.

Polarimetric photodetector can acquire higher resolution and more surface information of imaging targets in complex environments due to the identification of light polarization. To date, the existing technologies yet sustain the poor polarization sensitivity (<10), far from market application requirement. Here, the photovoltaic detectors with polarization- and gate-tunable optoelectronic reverse phenomenon are developed based on semimetal 1T'-MoTe2 and ambipolar WSe2 . The device exhibits gate-tunable reverse in rectifying and photovoltaic characters due to the directional inversion of energy band, yielding a wide range of current rectification ratio from 10-2 to 103 and a clear object imaging with 100 × 100 pixels. Acting as a polarimetric photodetector, the polarization ratio (PR) value can reach a steady state value of ≈30, which is compelling among the state-of-the-art 2D-based polarized detectors. The sign reversal of polarization-sensitive photocurrent by varying the light polarization angles is also observed, that can enable the PR value with a potential to cover possible numbers (1→+∞/-∞→-1). This work develops a photovoltaic detector with polarization- and gate-tunable optoelectronic reverse phenomenon, making a significant progress in polarimetric imaging and multifunction integration applications.

Drone swarm strategy for the detection and tracking of occluded targets in complex environments

Drone swarms can achieve tasks via collaboration that are impossible for single drones alone. Synthetic aperture (SA) sensing is a signal processing technique that takes measurements from limited size sensors and computationally combines the data to mimic sensor apertures of much greater widths. Here we use SA sensing and propose an adaptive real-time particle swarm optimization (PSO) strategy for autonomous drone swarms to detect and track occluded targets in densely forested areas. Simulation results show that our approach achieved a maximum target visibility of 72% within 14 seconds. In comparison, blind sampling strategies resulted in only 51% visibility after 75 seconds and 19% visibility in 3 seconds for sequential brute force sampling and parallel sampling respectively. Our approach provides fast and reliable detection of occluded targets, and demonstrates the feasibility and efficiency of using swarm drones for search and rescue in areas that are not easily accessed by humans, such as forests and disaster sites.

An unsupervised aerial tracking method of camouflaged targets in complex environments

With the widespread use of UAVs and the development of various technologies related to computer vision, much attention has been devoted to UAV-based target tracking. For the task of tracking camouflaged people in complex environments, there is a shortage of annotated datasets and poor backbone feature extraction network capabilities, which will cause tracking drift and tracking lag. To achieve unsupervised UAV target tracking under unsupervised conditions, a new target tracking model has been designed. First, we roughly detect moving targets using a camouflaged segmentation network, and then apply dynamic programming to generate smooth candidate boxes. Secondly, a deeper convolutional neural network is designed for feature extraction to replace the original backbone network, and the residual structure is modified to ensure tracking effectiveness. Extensive comparative experiments have shown that the proposed unsupervised method performs the task of UAV target tracking well.

SADENet: A supervised attention delicate enhanced network for subtle person detection

Object detection algorithms have been developed for decades, and one of remaining important challenges is the detection of subtle targets in complex environments. Many convolution neural network (CNN) based methods have been proposed to handle this problem. However, the information pertaining to subtle targets is delicate and can easily be lost or neglected in the upsampling and downsampling stages of conventional CNN. In this paper, we propose a new subtle target detection network, named the supervised attention delicate enhanced network (SADENet). Firstly, two sample vertebras are designed to solve the problem of information loss during upsampling and downsampling. Then, an enhanced context attention module (ECAM) is proposed, which extends the original supervised heatmap by fusing information from different scales. Based on the ECAM and the respective advantages of high-resolution and low-resolution feature maps, two effective sampling attention modules, the semantic fidelity upsampling module and the location enhancement downsampling module, are created to build a bi-directional connection neck structure. The effectiveness of our proposed method is demonstrated in experiments on the TinyPerson dataset, which outperforms many state-of-the-art detectors, especially in the detection of tiny and tiny1 scale targets.

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.

Development of a YOLO-KCF Coupling Algorithm for Miniature Fixed-Wing UAVs in Target Detection and Tracking

Target detection and tracking represent key challenges facing miniature fixed-wing unmanned aerial vehicles (UAVs), particularly at high cruising speeds. Therefore, this paper proposes a vision-based target detection and tracking algorithm that systematically couples two mainstream methods, namely, you only look once (YOLO) and kernel correlation filter (KCF) algorithms. This combination enables small fixed-wing UAVs to achieve reliable target detection and rapid target tracking. A customized vision-guidance module is constructed to implement this algorithm, and a dual-thread execution mechanism is developed to ensure that the computational resources are used effectively. A miniature fixed-wing UAV experimental platform is also constructed and evaluated. Flight experiments are performed, and the results demonstrate that the developed algorithm can achieve satisfactory detection and tracking accuracy for stationary and moving ground targets in complex environments.