DTS-YOLO: Enhancing Object Detection via Dynamic Routing, Texture Encoding, and Semantic Fusion

This paper presents a new automatic image segmentation method for segmenting moving object in complex environment by combining the motion information with edge information. We propose an adaptive optical flow method based on the Horn-Schunck algorithm to estimate the optical flow field. Our method puts different smoothness constraints on different directions and optical flow constraint is used according to the gradient magnitude. Canny edge detector can obtain the most edge information but miss some pixels. In order to restore these missing pixels the edge has a growing based on the continuity of optical flow field. Next, by remaining the block that has the longest edge could delete the noise in the background, and then the last segmentation result is obtained. The experimental result demonstrates that this method can segment the moving object in complex environment precisely.

Simultaneous Localization and Mapping (SLAM) is one of the fundamental functionalities for intelligent mobile robots. Over the last few decades, numerous impressive SLAM systems have been developed, demonstrating commendable performance in specific scenarios. However, some challenges still remain unsolved, such as how to handle moving objects in complex environments and how to enable robots to gain a true understanding of their surroundings and perform advanced tasks. This paper proposes a visual SLAM system, YOLOv7-SLAM, designed for complex environments with strong robustness. YOLOv7-SLAM employs a multi-threaded approach with five parallel threads: tracking, semantic segmentation, local mapping, loop closure, and dense semantic mapping creation. YOLOv7-SLAM employs the YOLO object detection method to remove obstacles in complex scenes, reducing the impact of obstacles in the environment and significantly enhancing localization accuracy in complex environments. We conducted experiments using the TUM RGB-D dataset. The results show that YOLOv7-SLAM achieves an order of magnitude improvement in absolute trajectory accuracy compared to ORB-SLAM2, making it one of the most advanced SLAM systems for complex environments. Our experiments were validated using the TUM RGB-D dataset. The results showcase a notable enhancement in the absolute trajectory accuracy of YOLOv7-SLAM in comparison to ORB-SLAM2 [1]. It performs well in complex obstacle-rich environments.

In this paper, we propose a full-automatic algorithm for extracting elongated object from CT image. Given an input image, we use the SWT(Stroke Width Transform) and MM(Mathematical Morphology) to locate the coarse location of target. Thus leading to over-segmentation. In order to refine the segmentation result, Levelset method is applied to make the contour fit the object. Experimental results show that the proposed algorithm gives precise contour in elongated object segmentation.

We propose a method for imaging small-scale diffraction objects in complex environments in which Kirchhoff-based approaches may fail. The proposed method is based on a separation between the specular reflection and diffraction components of the total wavefield in the migrated surface angle domain. Reverse-time migration was utilized to produce the common image gathers. This approach provides stable and robust results in cases of complex velocity models. The separation is based on the fact that, in surface angle common image gathers, reflection events are focused at positions that correspond to the apparent dip angle of the reflectors, whereas diffracted events are distributed over a wide range of angles. The high-resolution radon-based procedure is used to efficiently separate the reflection and diffraction wavefields. In this study, we consider poststack diffraction imaging. The advantages of working in the poststack domain are its numerical efficiency and the reduced computational time. The numerical results show that the proposed method is able to image diffraction objects in complex environments. The application of the method to a real seismic dataset illustrates the capability of the approach to extract diffractions.

A Personal Robot should be able to handle unknown objects in unknown environments. For a manipulation task the question what to do with an object once it had been grasped is one of the most essential ones beside the grasping task itself. Moreover, the planning time should be at least as fast as the time the robot needs for its motions. We propose a fast placement planner for sensor-modelled objects in complex environments. The planner computes a stable position and orientation for the object in the environment. The algorithm uses only geometric information, most notably no force or torque sensor is required. In particular, we introduce a novel approach regarding the pose computation. By means of experiments with various household objects the robustness and performance are validated. Further on, we compare our approach with a pose computation using a physics simulation framework.

Unmanned aerial vehicles (UAVs) have been widely used in post-disaster search and rescue operations, object tracking, and other tasks. Therefore, the autonomous perception of UAVs based on computer vision has become a research hotspot in recent years. However, UAV images include dense objects, small objects, and arbitrary object directions, which bring about significant challenges to existing object detection methods. To alleviate these issues, we propose a global-local feature enhanced network (GLF-Net). Considering the difficulty of processing UAV images with complex scenes and dense objects, we designed a backbone based on an involution and self-attention that can extract effective features from complex objects. A multiscale feature fusion module is also proposed to address the presence of numerous small objects in UAV images through multiscale object detection and feature fusion. To accurately detect rotated objects, a rotated regional proposal network was designed based on the midpoint offset representation, which can apply a rotated box to determine the real direction and contour of an object. GLF-Net achieves a state-of-the-art detection accuracy (86.52% mAP) on our created RO-UAV dataset, while achieving 96.95% and 97% mAP on the public datasets HRSC2016 and UCAS-AOU, respectively. The experimental results demonstrate that our method achieves a high detection accuracy and generalization, which can meet the practical requirements of UAVs under various complex scenarios.

Helmet detection is a critical component of road safety. However, existing detection algorithms face challenges in accuracy and recall, particularly when dealing with multi-scale objects in complex environments. To address these issues, this study proposes an improved YOLOv8-based model, denot-ed as BS-YOLO. Firstly, drawing inspiration from StarNet, we propose two modules, namely StarFuseBlock and StarSPPF, to enhance the feature extrac-tion capability of the model at shallow layers. Secondly, to mitigate the loss of texture features of small and medium-sized objects during the feature propagation process, we propose ResBiBlock, which captures global features through residual connections and Biformer Attention. Finally, MPDIoU is employed as a superior alternative to CIoU to enhance computational effi-ciency and provide greater robustness in situations where predicted boxes do not align with ground-truth boxes. To validate the performance of the pro-posed model, a series of extensive experiments were performed on the TWHD dataset.Results show that the BS-YOLO yields a 2.2 increase in precision, a 2.8 improvement in recall, and a 2.2 enhancement in mAP compared to the YOLOv8 baseline. The experimental results indicate that the proposed improvements effectively enhance the performance of the baseline model, particularly in terms of robustness when dealing with multi-scale ob-jects in complex scenarios.

The railway perimeter is a key area for ensuring railway operational safety, and the intrusion of foreign objects seriously threatens the railway traffic safety. Considering the false and missed detections caused by the small size objects and the intricate background, this study proposed a detection approach called BCD-YOLO, based on YOLOv8. First, an enhanced dynamic sparse attention module was developed. It captures fine-grained details in the feature map and strengthens image context correlation, while reducing computational complexity. Second, the enhanced feature fusion module (CARAFE) was improved and T-CARAFE was constructed to replace the nearest neighbor linear interpolation method in YOLOv8, reducing the problem of feature loss during upsampling to improve the model’s capability of detecting small targets and feature catching capability. Finally, the DeepSORT object tracking algorithm was combined, which considered its trajectory and dwell time to determine whether an alarm is required, filtering out the effects of irrelevant objects in complex environments, and reducing the false alarm rate. The tracking ability of DeepSORT was further improved by introducing a shift window (Swin Transformer). In the experiment, the dataset defined a railway perimeter to simulate the actual railway perimeter environment, and only intruding objects within this perimeter were excluded. The results show that BCD-YOLO, compared with the original YOLOv8, has a precision improvement of 5.22%, recall rate improvement of 1.62%,mAP@0.5 improvement of 2.35%, and 105.5 frames per second. Combined with DeepSORT, the false detection rate is reduced by 16%, which satisfies the requirements of both accuracy and speed in railway object detection and effectively improves the problem of false and missed detections of small objects. Therefore, BCD-YOLO shows strong potential for deployment in intelligent railway monitoring systems, improving detection accuracy and reliability in complex environments while enhancing public safety by reducing intrusion-related risks.

This study focuses on developing advanced methods for the identification and classification of objects in complex environments. Over the past two years, there has been an increase in the use of advanced technologies in various challenging scenarios. This research is centered on accurately identifying targets and tracking them. The study addresses challenges related to object detection in multi-dimensional and intricate settings, taking into account natural conditions like rain and fog, as well as technical limitations such as camera capabilities. Special emphasis is placed on data collection for training the identification model, followed by extensive data preprocessing, including cleaning, labeling, and augmentation. The research employs YOLO and Deep Sport machine learning algorithms, focusing on improving the accuracy and reliability of target recognition and increasing data processing speed to minimize misidentification risks. The integration of YOLO, known for its quick real-time object detection, with Deep Sport, which excels in detailed feature extraction and classification, forms the basis of our methodology. This fusion is a complex combination of both models' strengths, with YOLO quickly identifying relevant objects and Deep Sport performing an in-depth analysis. The experimental phase involves extensive testing of the models in varied weather conditions and settings to evaluate performance under challenging circumstances. This work aims to enhance object identification techniques in complex environments, a critical aspect for the effectiveness of various advanced operations. The findings are expected to significantly contribute to the field by enabling quicker and more accurate target identification.

With a focus on complex environments, the present paper describes a new algorithm in rigid and non-rigid object tracking through color feature. Object tracking in these environments is taken into consideration as real-time applications, such as manufacturing, surveillance and monitoring, smart rooms, and so on, where partial or full occlusion sensibly occurs. As is obvious, the best color-based object tracking algorithm is now known, as the mean shift (MS) iterative procedure, to find the location of an object in image sequences. The algorithm performance is not unfortunately acceptable once objects in complex environments need to be tracked. In fact, the main aim of the present research is to improve the MS tracking algorithm, by proposing an improved convex kernel function, which is now realized in association with the Kalman filter approach (KFA). In the algorithm proposed here, the KFA is employed to solve the full occlusion problems since the speed for the objects is constant. Subsequently, the present investigated robust kernel function has been designed to dominate the low saturation and partial occlusion problems.

To reduce environmental pollution caused by improper waste disposal, efficient waste management solutions are essential. Traditional methods rely on manual monitoring, which is time-consuming and ineffective. Advancements in artificial intelligence and deep learning enable automated waste detection and localization, improving efficiency in waste management. Faster R-CNN, an advanced object detection model, enhances precision in recognizing and localizing waste in visual data. By utilizing deep learning techniques, waste detection achieves high accuracy, reducing dependence on manual inspections.The integration of Faster R-CNN with image processing techniques allows for real-time identification of waste objects in complex environments. Localization is achieved by drawing bounding boxes around detected waste, providing precise positional information. The Region Proposal Network (RPN) plays a key role in this process by generating candidate object regions through anchor boxes and refining them based on object scores. Tensor Flow’s Object Detection API facilitates model training and optimization, ensuring accurate recognition of waste materials. High-performance convolutional neural networks enhance feature extraction, distinguishing waste from non-waste objects effectively. The use of deep learning in image-based waste detection supports scalable waste management solutions.Automated waste detection and localization contribute to sustainable urban development by enabling proactive waste management strategies. The ability to accurately identify and mark waste locations enhances the efficiency of cleaning processes and reduces environmental hazards. By analyzing waste distribution patterns, authorities can optimize resource allocation and improve waste disposal planning. The adoption of AI-driven approaches in waste detection minimizes human effort while promoting a cleaner and healthier environment. Key Words: AI-Driven waste detection, Faster R-CNN, Region Proposal Network, TensorFlow object detection API, Image processing and Localization.

In the current methods of point cloud processing, there are still several limitations, particularly in achieving high precision and accuracy for large objects in complex environments. Existing techniques often struggle with incomplete or noisy data, leading to inaccurate contour extraction. In view of the challenges associated with the sparse and discrete nature of point clouds in complex environments, which lead to poor accuracy and stability in object contour extraction, this paper proposes a novel method for accurately extracting the contours of three-dimensional target point clouds. The method integrates high-resolution images with sparse point cloud information to address these issues. Firstly, the local characteristics of the point cloud are calculated, allowing for the selection of a contour point cloud. Next, depth information from two-dimensional images is obtained through a fuzzy mapping relationship. Finally, constraint conditions are established to derive a more accurate predicted value of the contour point cloud. Experiments demonstrate that the proposed method effectively improves the precision and accuracy of contour extraction for large objects, reducing measurement deviation by approximately 64.9% compared to using the original point cloud alone. Additionally, the method shows a more accurate completion effect on parts of the contour that are missing, underscoring its robustness and effectiveness in challenging scenarios.

An object pick-and-place system with a camera, a six-degree-of-freedom (DOF) robot manipulator, and a two-finger gripper is implemented based on the robot operating system (ROS) in this paper. A collision-free path planning method is one of the most fundamental problems that has to be solved before the robot manipulator can autonomously pick-and-place objects in complex environments. In the implementation of the real-time pick-and-place system, the success rate and computing time of path planning by a six-DOF robot manipulator are two essential key factors. Therefore, an improved rapidly-exploring random tree (RRT) algorithm, named changing strategy RRT (CS-RRT), is proposed. Based on the method of gradually changing the sampling area based on RRT (CSA-RRT), two mechanisms are used in the proposed CS-RRT to improve the success rate and computing time. The proposed CS-RRT algorithm adopts a sampling-radius limitation mechanism, which enables the random tree to approach the goal area more efficiently each time the environment is explored. It can avoid spending a lot of time looking for valid points when it is close to the goal point, thus reducing the computing time of the improved RRT algorithm. In addition, the CS-RRT algorithm adopts a node counting mechanism, which enables the algorithm to switch to an appropriate sampling method in complex environments. It can avoid the search path being trapped in some constrained areas due to excessive exploration in the direction of the goal point, thus improving the adaptability of the proposed algorithm to various environments and increasing the success rate. Finally, an environment with four object pick-and-place tasks is established, and four simulation results are given to illustrate that the proposed CS-RRT-based collision-free path planning method has the best performance compared with the other two RRT algorithms. A practical experiment is also provided to verify that the robot manipulator can indeed complete the specified four object pick-and-place tasks successfully and effectively.

This study aims to enhance object detection systems by comparing pre-trained classification models with custom-trained ones, focusing on task-based deep learning for image recognition. The problem addressed is the challenge of accurately detecting and classifying objects in complex environments where traditional recognition systems may fall short. The proposed solution leverages transfer learning utilizing pre-trained models like ResNet or VGGNet as feature extractors. By exploiting the convolutional layers of these models, the system captures common features for specific detection tasks. Experimental analyses on benchmark datasets confirm the efficacy of this approach, demonstrating improved detection accuracy and efficiency in various scenarios. Specifically, FasterRCNN achieves a mean Average Precision (mAP) of 78% on synthetic datasets and 74% on real datasets at an Intersection over Union (IoU) threshold of 0.5. This indicates FasterRCNN's superior performance in terms of accuracy, making it a strong candidate for applications requiring high detection accuracy.

Remote sensing object detection is a difficult task because it often requires real-time feedback through numerous objects in complex environments. In object detection, Feature Pyramids Networks (FPN) have been widely used for better representations based on a multi-scale problem. However, the multiple level features cause detectors’ structures to be complex and makes redundant calculations that slow down the detector. This paper uses a single-layer feature to make the detection lightweight and accurate without relying on Feature Pyramid Structures. We proposed a method called the Cross Stage Partial Strengthen Matching Detector (StrMCsDet). The StrMCsDet generates a single-level feature map architecture in the backbone with a cross stage partial network. To provide an alternative way of replacing the traditional feature pyramid, a multi-scale encoder was designed to compensate the receptive field limitation. Additionally, a stronger matching strategy was proposed to make sure that various scale anchors may be equally matched. The StrMCsDet is different from the conventional full pyramid structure and fully exploits the feature map which deals with a multi-scale encoder. Methods achieved both comparable precision and speed for practical applications. Experiments conducted on the DIOR dataset and the NWPU-VHR-10 dataset achieved 65.6 and 73.5 mAP on 1080 Ti, respectively, which can match the performance of state-of-the-art works. Moreover, StrMCsDet requires less computation and achieved 38.5 FPS on the DIOR dataset.