Obstacle Detection Method Research Articles

A Review of UAV Path-Planning Algorithms and Obstacle Avoidance Methods for Remote Sensing Applications

The rapid development of uncrewed aerial vehicles (UAVs) has significantly increased their usefulness in various fields, particularly in remote sensing. This paper provides a comprehensive review of UAV path planning, obstacle detection, and avoidance methods, with a focus on its utilisation in both single and multiple UAV platforms. The paper classifies the algorithms into two main categories: (1) global and local path-planning approaches in single UAVs; and (2) multi-UAV path-planning methods. It further analyses obstacle detection and avoidance methods, as well as their capacity to adapt, optimise, and compute efficiently in different operational environments. The outcomes highlight the advantages and limitations of each method, offering valuable information regarding their suitability for remote sensing applications, such as precision agriculture, urban mapping, and ecological surveillance. Additionally, this review also identifies limitations in the existing research, specifically in multi-UAV frameworks, and provides recommendations for future developments to improve the adaptability and effectiveness of UAV operations in dynamic and complex situations.

Low-altitude UAV obstacle detection method based on position constraint and attention

UAVs are widely used in low-altitude fields for tasks such as power inspection, search and rescue, and reconnaissance. Pre-detection of obstacles during flight is a safety guarantee for completing the given tasks. In order to meet the requirements of obstacle detection accuracy and position regression accuracy when UAVs are flying at low altitudes, a low-altitude UAV obstacle detection method based on position constraint and attention improvement is proposed. Firstly, the shortcomings of the position regression loss function are analyzed, and based on this, a loss function of separating scale loss and integrating direction constraint is proposed to optimize the regression process; secondly, the attention mechanism CBAM is improved, and a dual attention mechanism is proposed to strengthen the feature suppression interference and improve the detection performance. The experimental results show that the improved algorithm has improved mAP 2.28%and mAP@0.5:0.95 2.7%, and has shown better low-altitude obstacle detection performance in both detection accuracy and position regression accuracy.

Field Obstacle Detection and Location Method Based on Binocular Vision

When uncrewed agricultural machinery performs autonomous operations in the field, it inevitably encounters obstacles such as persons, livestock, poles, and stones. Therefore, accurate recognition of obstacles in the field environment is an essential function. To ensure the safety and enhance the operational efficiency of autonomous farming equipment, this study proposes an improved YOLOv8-based field obstacle detection model, leveraging depth information obtained from binocular cameras for precise obstacle localization. The improved model incorporates the Large Separable Kernel Attention (LSKA) module to enhance the extraction of field obstacle features. Additionally, the use of a Poly Kernel Inception (PKI) Block reduces model size while improving obstacle detection across various scales. An auxiliary detection head is also added to improve accuracy. Combining the improved model with binocular cameras allows for the detection of obstacles and their three-dimensional coordinates. Experimental results demonstrate that the improved model achieves a mean average precision (mAP) of 91.8%, representing a 3.4% improvement over the original model, while reducing floating-point operations to 7.9 G (Giga). The improved model exhibits significant advantages compared to other algorithms. In localization accuracy tests, the maximum average error and relative error in the 2–10 m range for the distance between the camera and five types of obstacles were 0.16 m and 2.26%. These findings confirm that the designed model meets the requirements for obstacle detection and localization in field environments.

Integrating deep reinforcement learning and improved artificial potential field method for safe path planning for mobile robots

Purpose This paper aims to address the safety concerns of path-planning algorithms in dynamic obstacle warehouse environments. It proposes a method that uses improved artificial potential fields (IAPF) as expert knowledge for an improved deep deterministic policy gradient (IDDPG) and designs a hierarchical strategy for robots through obstacle detection methods. Design/methodology/approach The IAPF algorithm is used as the expert experience of reinforcement learning (RL) to reduce the useless exploration in the early stage of RL training. A strategy-switching mechanism is introduced during training to adapt to various scenarios and overcome challenges related to sparse rewards. Sensor inputs, including light detection and ranging data, are integrated to detect obstacles around waypoints, guiding the robot toward the target point. Findings Simulation experiments demonstrate that the integrated use of IDDPG and the IAPF method significantly enhances the safety and training efficiency of path planning for mobile robots. Originality/value This method enhances safety by applying safety domain judgment rules to improve APF’s security and designing an obstacle detection method for better danger anticipation. It also boosts training efficiency through using IAPF as expert experience for DDPG and the classification storage and sampling design for the RL experience pool. Additionally, adjustments to the actor network’s update frequency expedite convergence.

Collaborative Obstacle Detection for Dual USVs Using MGNN-DANet with Movable Virtual Nodes and Double Attention

To reduce missed detections in LiDAR-based obstacle detection, this paper proposes a dual unmanned surface vessels (USVs) obstacle detection method using the MGNN-DANet template matching framework. Firstly, point cloud templates for each USV are created, and a clustering algorithm extracts suspected targets from the point clouds captured by a single USV. Secondly, a graph neural network model based on the movable virtual nodes is designed, introducing a neighborhood distribution uniformity metric. This model enhances the local point cloud distribution features of the templates and suspected targets through a local sampling strategy. Furthermore, a feature matching model based on double attention is developed, employing self-attention to aggregate the features of the templates and cross-attention to evaluate the similarity between suspected targets and aggregated templates, thereby identifying and locating another USV within the targets detected by each USV. Finally, the deviation between the measured and true positions of one USV is used to correct the point clouds obtained by the other USV, and obstacle positions are annotated through dual-view point cloud clustering. Experimental results show that, compared to single USV detection methods, the proposed method reduces the missed detection rate of maritime obstacles by 7.88% to 14.69%.

A real-time and high-accuracy railway obstacle detection method using lightweight CNN and improved transformer

With the sustained development of railway transportation, the urgent necessity to improve train operation safety makes obstacle detection become the research focus. However, existing railway obstacle detectors still face challenges in balancing detection accuracy and speed during the shunting process. In addition, they are not robust enough in real-world railway environments, especially in complex scenes involving small obstacles. To address these problems, this paper presents a real-time and high-accuracy railway obstacle detection model using lightweight CNN and improved transformer (RH-Net) for detecting railway obstacles efficiently to guarantee traffic safety. First, the Lightweight Feature Extraction Module (LEM) is designed to minimize the model’s computational load while maintaining its feature extraction ability. Then, the Improved Transformer Module (IFM) is developed to boost the model’s ability about stably extract global contextual information. Finally, the Enhanced Multi-Scale Feature Fusion Module (EFM) is proposed to optimize the detection of obstacles with different sizes, especially small objects. In the experiments on railway dataset, RH-Net achieves optimal detection performance on GeForce GTX 1080Ti (96.99% mAP and 135 FPS) and Jetson Xavier NX (97.02% mAP and 43 FPS), which is significantly superior to the existing detection models. Experimental results show that RH-Net has excellent detection ability, which can accurately and efficiently detect obstacles in complicated railway environments. Moreover, the experiments on MS COCO indicate that RH-Net can achieve more satisfactory detection performance than existing state-of-the-art methods. Therefore, the proposed model can be well-applied to more complex real-world scenes for multiple object detection.

Study on Obstacle Detection Method Based on Point Cloud Registration

Study on Obstacle Detection Method Based on Point Cloud Registration

Optimization of Unmanned Driving Obstacle Detection Method

Optimization of Unmanned Driving Obstacle Detection Method

A Review of Intel Real Sense-Based Obstacle Detection for Unmanned Ground Vehicles

Abstract: The process of obstacle detection involves the identification of obstacles that lie ahead in the route, Intel RealSense camera has been a prominent solution for identifying real-time applications in recent years. Autonomous Unmanned Ground Vehicle(UGVs) face a difficult time in detecting obstacles because of stationary objects, moving objects and adverse weather conditions. We need to get an accurate distance between the UGVs and obstacles, So Intel RealSense cameras use stereo vision to calculate the depth data. Based on D415, D435 and D455 Intel RealSense depth sensors, we have examined and compared various obstacle detection methods.

A Novel Obstacle Detection Method in Underground Mines Based on 3D LiDAR

A Novel Obstacle Detection Method in Underground Mines Based on 3D LiDAR

An obstacle detection method for dual USVs based on SGNN-RMEN registration of dual-view point clouds

This paper proposes an unsupervised obstacle detection method for dual unmanned surface vessels (USVs) using the SGNN-RMEN framework. The method utilizes dual-view point clouds captured by two USVs to improve the detection of small obstacles under the condition of a visible shore. Firstly, a siamese graph neural network (SGNN) is designed to extract global contour features. A specialized task of global contour consistency classification is employed to ensure the interpretability of these features. Secondly, a rotation matrices estimation network (RMEN) is utilized to estimate the optimal rotation transformation for aligning point clouds based on the global contour features of the dual-view point clouds. The overlap degree between the dual-view point clouds before and after registration is used as feedback to train the model, enabling unsupervised learning. Finally, a " gridding - filtering - clustering” method is applied to annotate the size and position of obstacles based on the registration of the dual-view point clouds. Comparative experiments on two datasets demonstrate the effectiveness of the proposed method in accurately extracting contour features, achieving precise dual-view point cloud registration, and improving the detection rate of small obstacles in nearshore environments. The method also exhibits strong adaptability in unfamiliar marine environments.

INVys: Indoor Navigation System for Persons with Visual Impairment Using RGB-D Camera

This research presents the INVys system aiming to solve the problem of indoor navigation for persons with visual impairment by leveraging the capabilities of an RGB-D camera. The system utilizes the depth information provided by the camera for micronavigation, which involves sensing and avoiding obstacles in the immediate environment. The INVys system proposes a novel auto-adaptive double thresholding (AADT) method to detect obstacles, calculate their distance, and provide feedback to the user to avoid them. AADT has been evaluated and compared to baseline and auto-adaptive thresholding (AAT) methods using four criteria: accuracy, precision, robustness, and execution time. The results indicate that AADT excels in accuracy, precision, and robustness, making it a suitable method for obstacle detection and avoidance in the context of indoor navigation for persons with visual impairment. In addition to micronavigation, the INVys system utilizes the color information provided by the camera for macro-navigation, which involves recognizing and following navigational markers called optical glyphs. The system uses an automatic glyph binarization method to recognize the glyphs and evaluates them using two criteria: accuracy and execution time. The results indicate that the proposed method is accurate and efficient in recognizing the optical glyphs, making it suitable for use as a navigational marker in indoor environments. Furthermore, the study also provides a correlation between the size of the glyphs, the distance of the recognized glyphs, the tilt condition of the recognized glyphs, and the accuracy of glyph recognition. These correlations define the minimum glyph size that can be practically used for indoor navigation for persons with visual impairment. Overall, this research presents a promising solution for indoor navigation for persons with visual impairment by leveraging the capabilities of an RGB-D camera and proposing novel methods for obstacle detection and avoidance and for recognizing navigational markers.

Accurate real-time obstacle detection of coal mine driverless electric locomotive based on ODEL-YOLOv5s

The accurate identification and real-time detection of obstacles have been considered the premise to ensure the safe operation of coal mine driverless electric locomotives. The harsh coal mine roadway environment leads to low detection accuracy of obstacles based on traditional detection methods such as LiDAR and machine learning, and these traditional obstacle detection methods lead to slower detection speeds due to excessive computational reasoning. To address the above-mentioned problems, we propose a deep learning-based ODEL-YOLOv5s detection model based on the conventional YOLOv5s. In this work, several data augmentation methods are introduced to increase the diversity of obstacle features in the dataset images. An attention mechanism is introduced to the neck of the model to improve the focus of the model on obstacle features. The three-scale prediction of the model is increased to a four-scale prediction to improve the detection ability of the model for small obstacles. We also optimize the localization loss function and non-maximum suppression method of the model to improve the regression accuracy and reduce the redundancy of the prediction boxes. The experimental results show that the mean average precision (mAP) of the proposed ODEL-YOLOv5s model is increased from 95.2 to 98.9% compared to the conventional YOLOv5s, the average precision of small obstacle rock is increased from 89.2 to 97.9%, the detection speed of the model is 60.2 FPS, and it has better detection performance compared with other detection models, which can provide technical support for obstacle identification and real-time detection of coal mine driverless electric locomotives.

One-shot domain adaptive real-time 3D obstacle detection in farmland based on semantic-geometry-intensity fusion strategy

By introducing deep learning, LiDAR-based solutions have achieved impressive accuracy in 3D obstacle detection. However, gathering and labeling sufficient samples is the precondition for the effectiveness of existing solutions. This precondition is difficult to satisfy in actual farmland due to the scarcity of distinctive obstacle samples as well as the time-consuming and specialized labeling process. In practice, detection models trained on specific datasets may fail to generalize well to real farmland, as they lack adaptability to different categories and scenes. To address this limitation, this paper proposes a novel one-shot domain adaptive real-time 3D obstacle detection method based on semantic-geometry-intensity fusion strategy. By introducing the concept of one-shot domain adaptation, the proposed method enables fine-grained 3D obstacle detection with just one sample per category. Specifically, a semantic-geometry-intensity space generator is designed to bridge the category gap between training and test samples. The integration of semantic-geometry-intensity space-based classifier and centerpoint-based anchor-free locator is designed to keep a decent balance between accuracy and efficiency. The switching between object sample enhancer and fusion point cloud generator is designed to handle distribution differences of both points and categories. The obstacle detection system designed based on the proposed method has been tested in real farmland, achieving an overall F1 score of 89.54% and a Frame Rate of 21.32 Frames Per Second (FPS). These experimental results demonstrate the high accuracy and efficiency of the proposed method in performing obstacle detection.

Obstacle Detection Method of Underground Electric Locomotive Rail Based on Instance Segmentation

Real-time and accurate obstacle detection is a vital technology for electric locomotives, especially as driverless vehicles are introduced. A method of obstacle detection for underground electric locomotive rail based on instance segmentation is developed to solve the problems of misdetection and missing detection, low detection accuracy, and slow detection speed of rail obstacles. The method of locating the track mask, demarcating the effective driving boundary, expanding the track mask, and forming the effective driving area is adopted to verify whether the target is an obstacle based on whether the target is located in the effective driving area, to avoid the problem of misdetection and missing detection of the target obstacle. The YOLACT++ (You Only Look At CoefficienTs) model is improved, and path augmentation and target classification loss function replacement strategies are adopted to enhance the model’s ability to detect target details and increase the accuracy of target segmentation. Compared with traditional image processing, this method can detect both straight rail and turnout. The mean average precision of boundary box mAP0.5(box) and mask mAP0.5(mask) of the improved YOLACT++ model reaches 98.52% and 98.55%, which is higher than that of the YOLACT++ model, and the detection frame rate reaches 21.9 frames per second.

Zero‐shot obstacle detection using panoramic vision in farmland

AbstractReliable obstacle detection is of great significance to the navigation technology of unmanned agricultural machinery. Currently, most of the previous works have achieved significant performance with the help of visual prior information of obstacles, where visual prior information refers to the visual features learned by models in the training stage. However, collecting enough annotated images for the training stage can be challenging. In the absence of annotated images, the current methods cannot perform optimally. To address the above problem, this paper presents a zero‐shot obstacle detection model based on the You Only Look Once X backbone, introducing the concept of zero‐shot learning into real‐time obstacle detection systems. Specifically, the cascade of encoder and decoder modules is appended to the presented model, and the integration of semantic space‐based classification and anchor‐free localization modules is used for zero‐shot obstacle detection. The feasibility of the proposed method was verified on the actual farmland test data set. The experimental results show that the F1 scores of the seen obstacle (e.g., people) and the unseen obstacle (e.g., agricultural machinery) are 96.22% and 94.66%, respectively. The average detection time for each panoramic image is 52.52 ms (equivalent to 19.04 FPS). The proposed obstacle detection method exhibits superior performance in the situation where training samples of the target category are not available. Notably, the proposed model not only performs the correct classification of unseen obstacles, but also improves the detection performance of both seen and unseen obstacles. The proposed method achieves a balance between accuracy and detection speed.

Improved VIDAR and machine learning-based road obstacle detection method

Improved VIDAR and machine learning-based road obstacle detection method

Advancing Simultaneous Localization and Mapping with Multi-Sensor Fusion and Point Cloud De-Distortion

This study addresses the challenges associated with incomplete or missing information in obstacle detection methods that employ a single sensor. Additionally, it tackles the issue of motion distortion in LiDAR point cloud data during synchronization and mapping in complex environments. The research introduces two significant contributions. Firstly, a novel obstacle detection method, named the point-map fusion (PMF) algorithm, was proposed. This method integrates point cloud data from the LiDAR, camera, and odometer, along with local grid maps. The PMF algorithm consists of two components: the point-fusion (PF) algorithm, which combines LiDAR point cloud data and camera laser-like point cloud data through a point cloud library (PCL) format conversion and concatenation, and selects the most proximate point cloud to the quadruped robot dog as the valid data; and the map-fusion (MF) algorithm, which incorporates local grid maps acquired using the Gmapping and OctoMap algorithms, leveraging Bayesian estimation theory. The local grid maps obtained by the Gmapping and OctoMap algorithms are denoted as map A and map B, respectively. This sophisticated methodology enables seamless map fusion, which significantly enhances the precision and reliability of the approach. Secondly, a motion distortion removal (MDR) method for LiDAR point cloud data based on odometer readings was proposed. The MDR method utilizes legged odometer data for linear data interpolation of the original distorted LiDAR point cloud data, facilitating the determination of the corresponding pose of the quadruped robot dog. Subsequently, the LiDAR point cloud data are then transformed to the quadruped robot dog coordinate system, efficiently mitigating motion distortion. Experimental results demonstrated that the proposed PMF algorithm achieved a 50% improvement in success rate compared to using only LiDAR or the PF algorithm in isolation, while the MDR algorithm enhanced mapping accuracy by 45.9% when motion distortion was taken into account. The effectiveness of the proposed methods was confirmed through rigorous experimentation.

Obstacle Detection Method Based on RSU and Vehicle Camera Fusion

Road obstacle detection is an important component of intelligent assisted driving technology. Existing obstacle detection methods ignore the important direction of generalized obstacle detection. This paper proposes an obstacle detection method based on the fusion of roadside units and vehicle mounted cameras and illustrates the feasibility of a combined monocular camera inertial measurement unit (IMU) and roadside unit (RSU) detection method. A generalized obstacle detection method based on vision IMU is combined with a roadside unit obstacle detection method based on a background difference method to achieve generalized obstacle classification while reducing the spatial complexity of the detection area. In the generalized obstacle recognition stage, a VIDAR (Vision-IMU based identification and ranging) -based generalized obstacle recognition method is proposed. The problem of the low accuracy of obstacle information acquisition in the driving environment where generalized obstacles exist is solved. For generalized obstacles that cannot be detected by the roadside unit, VIDAR obstacle detection is performed on the target generalized obstacles through the vehicle terminal camera, and the detection result information is transmitted to the roadside device terminal through the UDP (User Data Protocol) protocol to achieve obstacle recognition and pseudo-obstacle removal, thereby reducing the error recognition rate of generalized obstacles. In this paper, pseudo-obstacles, obstacles with a certain height less than the maximum passing height of the vehicle, and obstacles with a height greater than the maximum passing height of the vehicle are defined as generalized obstacles. Pseudo-obstacles refer to non-height objects that appear to be “patches” on the imaging interface obtained by visual sensors and obstacles with a height less than the maximum passing height of the vehicle. VIDAR is a vision-IMU-based detection and ranging method. IMU is used to obtain the distance and pose of the camera movement, and through the inverse perspective transformation, it can calculate the height of the object in the image. The VIDAR-based obstacle detection method, the roadside unit-based obstacle detection method, YOLOv5 (You Only Look Once version 5), and the method proposed in this paper were applied to outdoor comparison experiments. The results show that the accuracy of the method is improved by 2.3%, 17.4%, and 1.8%, respectively, compared with the other four methods. Compared with the roadside unit obstacle detection method, the speed of obstacle detection is improved by 1.1%. The experimental results show that the method can expand the detection range of road vehicles based on the vehicle obstacle detection method and can quickly and effectively eliminate false obstacle information on the road.

A Novel Day-to-Night Obstacle Detection Method for Excavators Based on Image Enhancement and Multisensor Fusion

Traditional excavator driving relies only on manual observation, resulting in increased hazards in unstructured environments. When the excavator works in a relatively dark environment, there will be potential risks for both the driver and the surrounding pedestrians. In order to address this issue, this study takes the advantages of three different sensors, including infrared cameras, RGB cameras, and lidar sensors, and proposes a novel day-to-night obstacle detection approach by fusing data from multiple sensors. For the dark environment at night, the infrared camera is adopted for the detection task. However, compared with RGB cameras, the infrared camera usually have lower resolutions, making it difficult to be directly applied for the obstacle detection. Therefore, an image enhancement processing method for low-resolution infrared images is developed based on the Difference of Gaussian (DoG). Then, an image recognition method based on YOLO-v5 is proposed to detect images after image enhancement. Finally, a multi-sensor fusion method is suggested to identify the semantic information and 3D coordinates of objects. Experimental studies are carried out to assess image quality and the effectiveness of various object recognition tasks. The results of the experiments demonstrate that our method is capable of not only accurately extracting pedestrian position information from a complicated background environment and realizing timely pedestrian alarms, but also maintaining detection performance in an excavator working environment at night.