Oriented Bounding Box Object Detection Model Based on Improved YOLOv8

In the study of oriented bounding boxes(OBB)object detection in high-resolution remote sensing images,the problem of missed and wrong detection of small targets occurs because the targets are too small and have different orientations.Existing OBB object detection for remote sensing images,although making good progress,mainly focuses on directional modeling,while less consideration is given to the size of the object as well as the problem of missed detection.In this study,a method based on improved YOLOv8 was proposed for detecting oriented objects in remote sensing images,which can improve the detection precision of oriented objects in remote sensing images.Firstly,the ResCBAMG module was innovatively designed,which could better extract channel and spatial correlation information.Secondly,the innovative top-down feature fusion layer network structure was proposed in conjunction with the Efficient Channel Attention(ECA)attention module,which helped to capture inter-local cross-channel interaction information appropriately.Finally,we introduced an innovative ResCBAMG module between the different C2f modules and detection heads of the bottom-up feature fusion layer.This innovative structure helped the model to better focus on the target area.The precision and robustness of oriented target detection were also improved.Experimental results on the DOTA-v1.5 dataset showed that the detection Precision,mAP@0.5,and mAP@0.5:0.95 metrics of the improved model are better compared to the original model.This improvement is effective in detecting small targets and complex scenes.

Bounding box based on probability density for the pedestrian tracking

This paper proposes a pedestrian tracking approach using bounding box based on probability densities.It is generally a difficult task to track features like corner points in outdoor images due to complex environment.To solve this problem,the feature points are projected along X and Y direction separately,and a histogram is constructed for each projection,with horizontal axis as positions and vertical axis as the number of feature points that lie on each position.Finally,the vertical axis is normalized for expression as probability.After histogram is constructed,the probability of each feature point is checked with a threshold.A feature point will be ignored if its probability is lower than a threshold,while the remaining feature points are grouped,based on which a bounding box is made.Kanade-Lucas Tomasi(KLT)algorithm is adopted as the tracking algorithm because it is able to track local features in images robustly.The efficiency of the tracking results using this method is verified in real environment test.

LiDAR-based estimation of bounding box coordinates using Gaussian process regression and particle swarm optimization

Camera-based object tracking systems in a given closed environment lack privacy and confidentiality.In this study,light detection and ranging(LiDAR)was applied to track objects similar to the camera tracking in a closed environment,guaranteeing privacy and confidentiality.The primary objective was to demonstrate the efficacy of the proposed technique through carefully designed experiments conducted using two scenarios.In Scenario I,the study illustrates the capability of the proposed technique to detect the locations of multiple objects positioned on a flat surface,achieved by analyzing LiDAR data collected from several locations within the closed environment.Scenario II demonstrates the effectiveness of the proposed technique in detecting multiple objects using LiDAR data obtained from a single,fixed location.Real-time experiments are conducted with human subjects navigating predefined paths.Three individuals move within an environment,while LiDAR,fixed at the center,dynamically tracks and identifies their locations at multiple instances.Results demonstrate that a single,strategically positioned LiDAR can adeptly detect objects in motion around it.Furthermore,this study provides a comparison of various regression techniques for predicting bounding box coordinates.Gaussian process regression(GPR),combined with particle swarm optimization(PSO)for prediction,achieves the lowest prediction mean square error of all the regression techniques examined at 0.01.Hyperparameter tuning of GPR using PSO significantly minimizes the regression error.Results of the experiment pave the way for its extension to various real-time applications such as crowd management in malls,surveillance systems,and various Internet of Things scenarios.

A New Method to Extract Text from Natural Scenes

This paper presents a new method for text detection, location and binarization from natural scenes. Several morphological steps are used to detect the general position of the text, including English, Chinese and Japanese characters. Next bonnding boxes are processed by a new “Expand, Break and Merge” （EBM） method to get the precise text areas. Finally, text is binarized by a hybrid method based on Otsu and Niblack. This new approach can extract different kinds of text from complicated natural scenes. It is insensitive to noise, distortedness, and text orientation. It also has good performance on extracting texts in various sizes.

CAD Model-Based Intelligent Inspection Planning for Coordinate Measuring Machines

As the market competition among enterprises grows intensively and the demand for high quality products increases rapidly, product quality inspection and control has become one of the most important issues of manufacturing, and improving the efficiency and accuracy of inspection is also one of problems which enterprises must solve. It is particularly important to establish rational inspection planning for parts before inspecting product quality correctly. The traditional inspection methods have been difficult to satisfy the requirements on the speed and accuracy of modern manufacturing, so CAD-based computer-aided inspection planning （CAIP） system with the coordinate measuring machines （CMM） came into being. In this paper, an algorithm for adaptive sampling and collision-free inspection path generation is proposed, aiming at the CAD model-based inspection planning for coordinate measuring machines （CMM）. Firstly, using the method of step adaptive subdivision and iteration , the sampling points for the specified number with even distribution will be generated automatically. Then, it generates the initial path by planning the inspection sequence of measurement points according to the values of each point＇s weight sum of parameters, and detects collision by constructing section lines between the probe swept-volume surfaces and the part surfaces, with axis-aligned bounding box （AABB） filtering to improve the detection efficiency. For collided path segments, it implements collision avoidance firstly aiming at the possible outer-circle features, and then at other collisions, for which the obstacle-avoiding movements are planned with the heuristic rules, and combined with a designed expanded AABB to set the obstacle-avoiding points. The computer experimental results show that the presented algorithm can plan sampling points＇ locations with strong adaptability for different complexity of general surfaces, and generate efficient optimum path in a short time and avoid collision effectively.

Bounding box extraction from spherical hologram of elementary object to synthesize hologram of arbitrary three-dimensional scene with occlusion consideration(Invited Paper)

A novel method to extract a bounding box that contains the three-dimensional object from its spherical hologram is proposed. The proposed method uses the windowed Fourier transform to obtain the angular distribution of the quasi-collimated beams at each position in the spherical hologram and estimates the bounding box by accumulating the quasi-collimated beams in the volume inside the spherical hologram. The estimated bounding box is then used to realize occlusion effect between the objects in the synthesis of the three-dimensional scene hologram.

Approximating interior bounded box of 3D character mesh model based on its skeleton and symmetry

Purpose – In the process of robot shell design, it is necessary to match the shape of the input 3D originalcharacter mesh model and robot endoskeleton, in order to make the input model fit for robot and avoidcollision. So, the purpose of this paper is to find an object of reference, which can be used for the process ofshape matching.Design/methodology/approach – In this work, the authors propose an interior bounded box (IBB)approach that derives from oriented bounding box (OBB). This kind of box is inside the closed mesh model.At the same time, it has maximum volume which is aligned with the object axis but is enclosed by all the meshvertices. Based on the IBB of input mesh model and the OBB of robot endoskeleton, the authors can completethe process of shape matching. In this paper, the authors use an evolutionary algorithm, covariance matrixadaptation evolution strategy (CMA-ES), to approximate the IBB based on skeleton and symmetry of inputcharacter mesh model.Findings – Based on the evolutionary algorithm CMA-ES, the optimal position and scale informationof IBB can be found. The authors can obtain satisfactory IBB result after this optimization process.The output IBB has maximum volume and is enveloped by the input character mesh model as well.Originality/value – To the best knowledge of the authors, the IBB is first proposed and used in the field ofrobot shell design. Taking advantage of the IBB, people can quickly obtain a shell model that fit for robot.At the same time, it can avoid collision between shell model and the robot endoskeleton.