Occlusion Scenarios Research Articles

Multi-scenario Vehicle Detection Based on the YOLOv5 Algorithm

This paper addresses the issues of increasing traffic volume leading to frequent traffic congestion and accidents by studying the effectiveness of occluded vehicle detection based on the YOLOv5 algorithm. The aim is to explore the performance of this algorithm in various occlusion scenarios. Firstly, we introduce the occluded vehicle images used for testing and describe different types of occlusions in detail. Then, the basic principles and construction process of the YOLOv5 algorithm are explained. Subsequently, we propose a vehicle detection and recognition model based on YOLOv5 and validate the model's effectiveness through convergence analysis of the training loss curve and accuracy analysis of the test set. Finally, experimental results demonstrate that the YOLOv5 algorithm can efficiently and accurately detect vehicles in complex scenarios and partially occluded conditions, showcasing its application potential in intelligent transportation systems.

Learning adaptive shift and task decoupling for discriminative one-step person search

Mainstream person search models aim to jointly optimize person detection and re-identification (ReID) in a one-step manner. Despite notable progress, existing one-step person search models still face three major challenges in extracting discriminative features: 1) incomplete feature extraction and fusion hinder the effective utilization of multiscale information, 2) the models struggle to capture critical features in complex occlusion scenarios, and 3) the optimization objectives of person detection and ReID are in conflict in the shared feature space. To address these issues, this study proposes a novel adaptive shift and task decoupling (ASTD) method that aims to enhance the accuracy and robustness of extracting discriminative features within the region of interest. In particular, we introduce a scale-aware transformer to handle scale/pose variations and occlusions. This transformer incorporates scale-aware modulation to enhance the utilization of multiscale information and adaptive shift augmentation to learn adaptation to occlusions dynamically. In addition, we design a task decoupling mechanism to hierarchically learn independent task representations using orthogonal loss to decouple two subtasks during training. Experimental results show that ASTD achieves state-of-the-art performance on the CUHK-SYSU and PRW datasets. Our code is accessible at https://github.com/zqx951102/ASTD.

Enhancing capture efficiency of drug-carrier particles in the carotid sinus by utilizing a combination of magnetic fields: A numerical approach

Magnetic drug targeting is a relatively new method to treat vascular occlusion in different body parts. However, the effectiveness of this method can be affected due to the severity and location of the occlusion. This can lead to the injection of high dosages of drugs, which can cause serious side effects due to the deposition of drugs in unwanted parts. To mitigate these effects, this study investigates the potential of a guiding magnetic field in enhancing drug absorption for vascular occlusion treatment. The method relies on guiding magnetic nanoparticles (NPs) loaded with drugs toward the occlusion site using two external magnetic fields. Blood flow was modeled as non-Newtonian, considering shear-rate-dependent viscosity and unsteady at the inlet. To test this idea, a computational fluid dynamic (CFD) coupled with a discrete phase model (DPM) approach has been employed to simulate drug delivery in three-vessel structures with varying degrees of occlusion (45 %, 60 %, and 90 %). To avoid the escape of drug carriers, a secondary magnetic field was applied at the bifurcation point to direct the NPs to the site of blockage where the primary magnetic field acts. Then, the states with or without a guiding source at the bifurcation site are compared based on the capture efficiency of each structure. The simulation demonstrated a significant increase in NP capture at the target site, ranging from 2 % to 15 %, depending on the NP size. However, the severity of occlusion substantially impacted the secondary magnetic field's effectiveness. In the 90 % occlusion scenario, the method's efficiency decreased significantly from 26 % to 16 % for NP sizes exceeding 1.5μm. This study highlights the potential of guiding magnetic fields in improving drug delivery to target sites in vascular occlusion.

PSPMoni: A Robust Wear Monitoring Method of Pantograph Slide Plate

The pantograph slide plate (PSP) plays a crucial role in the daily maintenance of trains by transmitting electrical energy from the contact wire (CW) to the train. Automatic monitoring of PSP wear condition is essential to notice abnormal wear promptly. In field applications, the target PSP edge may be obscured by the rear side PSP due to the operating attitude of the pantograph, leading to false detections and interfering with the field maintenance work. Meanwhile, the scenario of the PSP occlusion is characterized by randomness, which brings a considerable challenge to the reconstruction of the occluded edges. A robust PSP wear monitoring method is proposed to improve the performance of wear detection in field applications, considering the PSP occlusion scenarios. Firstly, the wear area of the PSP is localized using the YOLOv5s model. Subsequently, a fusion of the morphology method and the Canny operator is employed to extract the edge of the PSP. Different occlusion types are identified through detailed observation, and corresponding edge reconstruction methods are proposed for occluded edges. Finally, a robust wear condition evaluation method and five evaluation criteria for assessing wear condition are introduced. Experimental results demonstrate that the system achieves accurate PSP wear detection with an accuracy of 0.6 mm, and the reconstructed edge at occlusion locations closely matches the target edge compared to other automatic systems.

Reverse Pyramid Attention Guidance Network for Person Re-Identification

Person re-identification aims to retrieve pedestrians with the same identity across different cameras. However, current methods increase attention to interfering regions when dealing with complex backgrounds and occlusion, especially in the presence of similar interfering features. To enhance the robustness of the model, we propose the Reverse Pyramid Attention Guidance (RPAG) network, using a reverse pyramid structure to learn features at multiple granularities. To mitigate the impact of occlusion, we introduce the Similar Feature Filtering (SFF) attention module at the pixel level, using graph convolution to adaptively select occluded regions, thereby enhancing retrieval accuracy by filtering out irrelevant parts. Combining the reverse pyramid structure with the pixel-level attention module strengthens adaptability to complex scenes, guides multi-granularity feature learning, and effectively handles various occlusion scenarios. RPAG achieved Rank-1 accuracies of 96.2%, 93.2%, 88.7%, and 73.2% on the Market1501, DukeMTMC-ReID, MSMT17, and Occluded-Duke datasets, respectively.

A Hybrid Neuromorphic Object Tracking and Classification Framework for Real-Time Systems.

Deep learning inference that needs to largely take place on the "edge" is a highly computational and memory intensive workload, making it intractable for low-power, embedded platforms such as mobile nodes and remote security applications. To address this challenge, this article proposes a real-time, hybrid neuromorphic framework for object tracking and classification using event-based cameras that possess desirable properties such as low-power consumption (5-14 mW) and high dynamic range (120 dB). Nonetheless, unlike traditional approaches of using event-by-event processing, this work uses a mixed frame and event approach to get energy savings with high performance. Using a frame-based region proposal method based on the density of foreground events, a hardware-friendly object tracking scheme is implemented using the apparent object velocity while tackling occlusion scenarios. The frame-based object track input is converted back to spikes for TrueNorth (TN) classification via the energy-efficient deep network (EEDN) pipeline. Using originally collected datasets, we train the TN model on the hardware track outputs, instead of using ground truth object locations as commonly done, and demonstrate the ability of our system to handle practical surveillance scenarios. As an alternative tracker paradigm, we also propose a continuous-time tracker with C++ implementation where each event is processed individually, which better exploits the low latency and asynchronous nature of neuromorphic vision sensors. Subsequently, we extensively compare the proposed methodologies to state-of-the-art event-based and frame-based methods for object tracking and classification, and demonstrate the use case of our neuromorphic approach for real-time and embedded applications without sacrificing performance. Finally, we also showcase the efficacy of the proposed neuromorphic system to a standard RGB camera setup when simultaneously evaluated over several hours of traffic recordings.

Study on intelligent anti-occlusion tracking algorithm for infrared ground targets

In response to the issue of infrared ground target tracking failure caused by background occlusion, a novel anti-occlusion tracker for infrared ground targets is proposed based on an enhanced trajectory prediction network. Initially, an occlusion assessment criterion is proposed to accurately assess the occlusion status of infrared ground targets. Subsequently, enhancements are made to the BiTrap trajectory prediction network. On one hand, velocity information is introduced through a Siamese network structure, adopting a unidirectional prediction method, building the SiamTrap trajectory prediction network that improves trajectory prediction accuracy. On the other hand, refining both the training and application methods enables more precise predictions of ground target trajectories. For short-term occlusion, the SiamTrap network uses temporal context information to predict the occluded position of the target. For long-term occlusion, a search expansion strategy is introduced to address prediction errors accumulated due to a lack of real target information. Finally, a "second verification" criterion is introduced, realizing accurate target capture and normal tracking. Comparative tests are conducted on infrared target tracking sequences with occlusion. Compared to baseline trackers, the proposed algorithm shows a 5.2% improvement in success rate and a 5.9% improvement in accuracy under the OPE evaluation metric. This indicates the robustness of the proposed algorithm in handling occlusion scenarios for infrared ground targets.

LiDARCapV2: 3D human pose estimation with human–object interaction from LiDAR point clouds

Human–object interactions in open environments are common in the real world. Estimating 3D human pose from data where objects occlude the human is a challenging task in biometrics. However, existing LiDAR-based human motion capture datasets lack occlusion scenarios between humans and objects. To overcome this limitation, we propose LiDARHuman51M, a new human–object interaction dataset captured by LiDAR in long-range outdoor scene. It includes human motion labels acquired by an IMU system and synchronous RGB images. Additionally, we present an occlusion-aware method, LiDARCapV2, for capturing human motion from LiDAR point clouds under human–object interaction settings. Our key insight is to overcome object interference in human feature extraction by introducing a module called AgNoise-Segment. A noise augmentation strategy introduced in the AgNoise-Segment module alleviates the dependency of the segmentation accuracy on the effectiveness of 3D human pose estimations. Furthermore, we propose a skeleton extraction module that integrates features learned from the AgNoise-Segment module and predicts the skeleton locations. Quantitative and qualitative experiments demonstrate that LiDARCapV2 can capture high-quality 3D human motion under human–object interaction settings. Experiments on the KITTI and Waymo datasets demonstrate that our method can be generalized to real-world open scenarios.

A multi-sensor fusion framework for localization using LiDAR, IMU and RGB-D camera

Abstract In recent years, the increasing demand for precise and intelligent systems has been driven by advancements in indoor unmanned
navigation and positioning technologies. Nonetheless, the indoor environment poses challenges as objects often intersect or obstruct
each other due to spatial constraints, significantly impeding sensor recognition capabilities and compromising localization accuracy.
This paper presented a multi-sensor fusion framework within a system primarily comprised of LiDAR, complemented by RGB D and IMU sensors, to mitigate these challenges. To mitigate point cloud misalignment arising from occlusions, an improved PL-ICP algorithm have been proposed, resulting in improved accuracy and speed in occlusion scenarios. Meanwhile, this paper enhanced the Otsu algorithm by leveraging RGB-D matching to extract additional feature information, consequently enhancing the system’s convergence when occlusion happens. Ultimately, the Extended Kalman Filter (EKF) algorithm is employed to fuse point cloud and image data. Extensive experimental results demonstrate that the proposed approach not only enhances localization accuracy and stability but also exhibits superior convergence characteristics, offering an economical and efficient solution for robotic navigation.

Graph neural network based human detection in videos during occlusion environments

One of the most difficult perceptual problems for many applications is accurately recognizing the human object in a variety of circumstances. This can be difficult due to obstructions, weather, complex backdrops, cast shadows, and occlusions. Occlusion is a challenging open problem where a detector can only perceive a portion of the target human because of obstacles in the surrounding. In this research, an experimental investigation was conducted using the multi object tracking (MOT17) datasets to construct a graph neural network-based solution for the detection of humans in videos while considering the possibility of occlusion. Graph neural network (GNN) is used for the construction of neural solver model for detecting human object in occlusion scenario. The results obtained shows that this proposed method offers a considerable improvement in efficiency in comparison to the ways that have been used in the past. The values obtained for the standard performance metrics are higher than the state-of-the-art methods.

Consensus-Based Information Filtering in Distributed LiDAR Sensor Network for Tracking Mobile Robots.

A distributed state observer is designed for state estimation and tracking of mobile robots amidst dynamic environments and occlusions within distributed LiDAR sensor networks. The proposed novel framework enhances three-dimensional bounding box detection and tracking utilizing a consensus-based information filter and a region of interest for state estimation of mobile robots. The framework enables the identification of the input to the dynamic process using remote sensing, enhancing the state prediction accuracy for low-visibility and occlusion scenarios in dynamic scenes. Experimental evaluations in indoor settings confirm the effectiveness of the framework in terms of accuracy and computational efficiency. These results highlight the benefit of integrating stationary LiDAR sensors' state estimates into a switching consensus information filter to enhance the reliability of tracking and to reduce estimation error in the sense of mean square and covariance.

YOLOv5s-CEDB: A robust and efficiency Camellia oleifera fruit detection algorithm in complex natural scenes

To solve the problem of poor recognition accuracy caused by various colors, uneven distribution, and occlusion by branches and leaves of Camellia oleifera fruits under natural growth conditions, this study proposes an improved deep learning network, YOLOv5s-CEDB, for Camellia oleifera fruit detection based on YOLOv5s. Coordinate Attention Mechanism (CoordAtt), Deformable Convolution (DConv), and Explicit Visual Center (EVC) are introduced to enhance the network’s local and global feature extraction performance. To improve the detection performance for small and dense targets, the feature fusion module of the network was replaced with the designed light-bidirectional feature pyramid (light-BiFPN) structure. GhostConv was used to reduce the parameters and inference speed of the structure. A dataset with different light conditions, colors, and density levels of Camellia oleifera fruits was established, and performance evaluation experiments were conducted. Experimental results showed that the mean Average Precision (mAP) and F1-score of the designed YOLOv5s-CEDB network reached 91.4 % and 89.6 %, respectively, which were 2.6 % and 3.6 % higher than those of the original YOLOv5s model, respectively, and the influencing frame rate arrived at 37.6 FPS. Under different colors, distribution densities, occlusion scenarios, and light intensities, the detection accuracy of the YOLOv5s-CEDB network model was significantly better than those of the YOLOv5s, YOLOv8s and Faster-RCNN networks. It was verified that the proposed YOLOv5s-CEDB network could significantly improve the accuracy and stability of Camellia oleifera fruit detection, satisfying the requirements of yield estimation and intelligent harvesting.

AOPPI: An adaptive obstruction perception pedestrian identifier for complex environments

Pedestrian detection plays a crucial role in ensuring traffic safety within the domain of computer vision. However, accurately detecting pedestrians in complex environments proves to be a challenge due to issues such as occlusion. To address this issue, this paper presents an end-to-end pedestrian detection model founded on the DEtection TRansformer (DETR) architecture, effectively managing occlusion scenarios. The proposed model comprises a backbone Convolutional Neural Network (CNN) and a Transformer network. The backbone CNN incorporates variable convolution and U-Net design principles to enhance feature extraction capabilities, particularly for occluded pedestrians. Additionally, our innovative Adaptive Occlusion-Aware Attention Mechanism (AOAM) is embedded within the Transformer network, allowing the model to dynamically adjust attention weights and enhance the localization and identification of occluded pedestrians. Extensive experiments on the Caltech and ETH datasets demonstrate the superior performance of our model compared to state-of-the-art approaches across four key evaluation metrics. This study provides effective methodologies and theoretical foundations for pedestrian detection in complex environments.

Occlusion-aware collision avoidance trajectory planning with potential collision risk assessment for autonomous vehicle

Motion planning for autonomous vehicles relies heavily on perception and prediction results to find a safe, collision-free local trajectory that adheres to traffic rules. However, vehicle perception is frequently limited by occlusion, and the generation of safe local trajectories with restricted perception is a significant challenge in the field of motion planning. This paper introduces a collision avoidance trajectory planning algorithm that considers potential collision risks, within a hierarchical framework of sampling and optimization. The primary objective of this work is to generate trajectories that are safer and align better with human driver behavior while considering potential collision risks in occluded regions. Specifically, in occlusion scenarios, the state space is discretized, and a dynamic programming algorithm is used for a sampling-based search to obtain initial trajectories. Additionally, the concept of a driving risk field is introduced to describe potential collision risk elements within the human-vehicle-road environment. By drawing inspiration from graph search algorithms, potential collision risk areas are accurately described, and a cost function is proposed for evaluating potential risks in occluded regions. Drivers typically exhibit conservative and cautious driving behavior when navigating through occluded regions. The proposed algorithm not only prioritizes driving safety but also considers driving efficiency, thereby reducing the vehicle's conservativeness when passing through occlusions. The research results demonstrate that the ego vehicle can actively avoidblind spots and tends to move away from occluded regions, aligning more closely with human driver behavior.

Fast Coherent Video Style Transfer via Flow Errors Reduction

For video style transfer, naively applying still image techniques to process a video frame-by-frame independently often causes flickering artefacts. Some works adopt optical flow into the design of temporal constraint loss to secure temporal consistency. However, these works still suffer from incoherence (including ghosting artefacts) where large motions or occlusions occur, as optical flow fails to detect the boundaries of objects accurately. To address this problem, we propose a novel framework which consists of the following two stages: (1) creating new initialization images from proposed mask techniques, which are able to significantly reduce the flow errors; (2) process these initialized images iteratively with proposed losses to obtain stylized videos which are free of artefacts, which also increases the speed from over 3 min per frame to less than 2 s per frame for the gradient-based optimization methods. To be specific, we propose a multi-scale mask fusion scheme to reduce untraceable flow errors, and obtain an incremental mask to reduce ghosting artefacts. In addition, a multi-frame mask fusion scheme is designed to reduce traceable flow errors. In our proposed losses, the Sharpness Losses are used to deal with the potential image blurriness artefacts over long-range frames, and the Coherent Losses are performed to restrict the temporal consistency at both the multi-frame RGB level and Feature level. Overall, our approach produces stable video stylization outputs even in large motion or occlusion scenarios. The experiments demonstrate that the proposed method outperforms the state-of-the-art video style transfer methods qualitatively and quantitatively on the MPI Sintel dataset.

Deep-feature-based asymmetrical background-aware correlation filter for object tracking

Correlation filter-based video object-tracking algorithms have gained widespread attention due to their efficiency and excellent tracking performance. However, traditional correlation filtering tracking algorithms possess several limitations. (1) They extract image features only by using rule sampling, which ignores the shape information of the target, resulting in insufficient discriminative power of the features. (2) They focus only on the difference between the background and the object, ignoring the effects of more challenging intra-class interference. (3) They do not further evaluate the reliability of the optimal candidate samples, resulting in easy failure in occlusion scenarios. This paper proposes an asymmetric background-aware correlation filter method for object tracking with deep features to solve the above limitations. First, an asymmetrical background-aware sampling method based on the shape information of the object is proposed. This sampling method significantly differs from the symmetrical sampling method in the traditional correlation filter framework. By exploring the shape information of the object, improving the otherness between the background and object samples is easy, thus suppressing the intra-class interferences. Second, deep neural networks are introduced in the correlation filter framework to extract the deep object features and a spatio-temporal regularization factor is adaptively assigned to suppress the boundary effects, intra-class distractors and aberrance between frames. Finally, a multi-modal object pool is constructed to evaluate the optimal candidate sample in each frame. This template pool fully exploits object diversity and solves the tracking drift and failure caused by invalid appearance changes in scenes such as occlusion and vigorous motion scenarios. To validate the effectiveness of the proposed method, it was compared with the state-of-the-art methods on public datasets. The experimental results show that the tracking performance of the proposed method is competitive.

Focus and imagine: Occlusion suppression and repairing transformer for occluded person re-identification

Occlusion scenarios pose a great challenge to person re-identification (ReID) task because various occlusions may weaken the discriminative features and introduce interference. Recently, Transformer-based networks, which can aggregate features of all the image patches to construct global features adaptively, have shown advantages in occluded person ReID. Existing methods mainly adopted Transformer as a feature extractor and enhanced local features from the output of the Transformer encoder. However, during the processing of self-attention blocks, disturbing features from occlusions may be diffused into all the tokens, making it difficult to construct effective local features. Therefore, we consider predicting the occlusion situation of images before feature extraction and guiding the Transformer encoder to focus on visible regions, suppressing interference from occlusion. Furthermore, we propose to imagine the partial target under occlusion and reconstruct pseudo-holistic features for more robust retrieval. To this end, the Occlusion Suppression and Repairing Transformer (OSRTrans) is proposed. First, we use a self-supervised occlusion predictor to predict occlusion scores of image patches. Then the Occlusion Suppression Encoder (OSE), guided by occlusion predictions, suppresses the interference from occlusion regions and constructs a global feature. Finally, inspired by contrastive learning, the Feature Repairing Head (FRH) is proposed to reconstruct pseudo-holistic features. Our method enhances model’s ability of extracting discriminative local features, and achieve the state-of-the-art performance on occluded person ReID benchmarks, e.g., Rank-1 of 72.9% on Occluded-DukeMTMC.

Automatic Feature Construction-Based Genetic Programming for Degraded Image Classification

Accurately classifying degraded images is a challenging task that relies on domain expertise to devise effective image processing techniques for various levels of degradation. Genetic Programming (GP) has been proven to be an excellent approach for solving image classification tasks. However, the program structures designed in current GP-based methods are not effective in classifying images with quality degradation. During the iterative process of GP algorithms, the high similarity between individuals often results in convergence to local optima, hindering the discovery of the best solutions. Moreover, the varied degrees of image quality degradation often lead to overfitting in the solutions derived by GP. Therefore, this research introduces an innovative program structure, distinct from the traditional program structure, which automates the creation of new features by transmitting information learned across multiple nodes, thus improving GP individual ability in constructing discriminative features. An accompanying evolution strategy addresses high similarity among GP individuals by retaining promising ones, thereby refining the algorithm’s development of more effective GP solutions. To counter the potential overfitting issue of the best GP individual, a multi-generational individual ensemble strategy is proposed, focusing on constructing an ensemble GP individual with an enhanced generalization capability. The new method evaluates performance in original, blurry, low contrast, noisy, and occlusion scenarios for six different types of datasets. It compares with a multitude of effective methods. The results show that the new method achieves better classification performance on degraded images compared with the comparative methods.

Efficacy and safety of hyperbaric oxygen therapy in acute ischaemic stroke: a systematic review and meta-analysis

ObjectiveThis study aims to evaluate the efficacy and safety of adjunctive hyperbaric oxygen therapy (HBOT) in acute ischaemic stroke (AIS) based on existing evidence.MethodsWe conducted a comprehensive search through April 15, 2023, of seven major databases for randomized controlled trials (RCTs) comparing adjunctive hyperbaric HBOT with non-HBOT (no HBOT or sham HBOT) treatments for AIS. Data extraction and assessment were independently performed by two researchers. The quality of included studies was evaluated using the tool provided by the Cochrane Collaboration. Meta-analysis was conducted using Rev Man 5.3.ResultsA total of 8 studies involving 493 patients were included. The meta-analysis showed no statistically significant differences between HBOT and the control group in terms of NIHSS score (MD = -1.41, 95%CI = -7.41 to 4.58), Barthel index (MD = 8.85, 95%CI = -5.84 to 23.54), TNF-α (MD = -5.78, 95%CI = -19.93 to 8.36), sICAM (MD = -308.47, 95%CI = -844.13 to 13227.19), sVCAM (MD = -122.84, 95%CI = -728.26 to 482.58), sE-selectin (MD = 0.11, 95%CI = -21.86 to 22.08), CRP (MD = -5.76, 95%CI = -15.02 to 3.51), adverse event incidence within ≤ 6 months of follow-up (OR = 0.98, 95%CI = 0.25 to 3.79). However, HBOT showed significant improvement in modified Rankin score (MD = 0.10, 95%CI = 0.03 to 0.17), and adverse event incidence at the end of treatment (OR = 0.42, 95%CI = 0.19 to 0.94) compared to the control group.ConclusionWhile our findings do not support the routine use of HBOT for improving clinical outcomes in AIS, further research is needed to explore its potential efficacy within specific therapeutic windows and for different cerebral occlusion scenarios. Therefore, the possibility of HBOT offering clinical benefits for AIS cannot be entirely ruled out.

AG-YOLO: A Rapid Citrus Fruit Detection Algorithm with Global Context Fusion

Citrus fruits hold pivotal positions within the agricultural sector. Accurate yield estimation for citrus fruits is crucial in orchard management, especially when facing challenges of fruit occlusion due to dense foliage or overlapping fruits. This study addresses the issues of low detection accuracy and the significant instances of missed detections in citrus fruit detection algorithms, particularly in scenarios of occlusion. It introduces AG-YOLO, an attention-based network designed to fuse contextual information. Leveraging NextViT as its primary architecture, AG-YOLO harnesses its ability to capture holistic contextual information within nearby scenes. Additionally, it introduces a Global Context Fusion Module (GCFM), facilitating the interaction and fusion of local and global features through self-attention mechanisms, significantly improving the model’s occluded target detection capabilities. An independent dataset comprising over 8000 outdoor images was collected for the purpose of evaluating AG-YOLO’s performance. After a meticulous selection process, a subset of 957 images meeting the criteria for occlusion scenarios of citrus fruits was obtained. This dataset includes instances of occlusion, severe occlusion, overlap, and severe overlap, covering a range of complex scenarios. AG-YOLO demonstrated exceptional performance on this dataset, achieving a precision (P) of 90.6%, a mean average precision (mAP)@50 of 83.2%, and an mAP@50:95 of 60.3%. These metrics surpass existing mainstream object detection methods, confirming AG-YOLO’s efficacy. AG-YOLO effectively addresses the challenge of occlusion detection, achieving a speed of 34.22 frames per second (FPS) while maintaining a high level of detection accuracy. This speed of 34.22 FPS showcases a relatively faster performance, particularly evident in handling the complexities posed by occlusion challenges, while maintaining a commendable balance between speed and accuracy. AG-YOLO, compared to existing models, demonstrates advantages in high localization accuracy, minimal missed detection rates, and swift detection speed, particularly evident in effectively addressing the challenges posed by severe occlusions in object detection. This highlights its role as an efficient and reliable solution for handling severe occlusions in the field of object detection.