Line Segment and Circular Arc Extractions for Object Recognition with Floating Ballot Box

Finding efficient and powerful techniques for representing 2D and 3D entities is central in many areas, such as computer vision, graphics, CAD or data visualization. The large amount of data often involved and the small processing time required place strong demands on modeling techniques. This chapter gives an overview of the possibilities wavelets offer for object modeling, specially from the point of view of object recognition in computer vision environments. For the 2D case, techniques based on segmented contours or raw grey level information are described. For 3D data, both the cases of dense, regularly sampled volumetric information and sparse, irregularly sampled geometric surface information are considered. Ideas on how Bayesian methods may enhance wavelet based techniques for object representation and recognition are outlined.

The extraction of component line segments and circular arcs from freehand strokes along with their relations is a prerequisite for sketch understanding. Existing approaches usually take three stages to segment a stroke: first identifying segmentation points, then classifying the substroke between each pair of adjacent segmentation points, and, finally, obtaining graphical representations of substrokes by fitting graphical primitives to them. Since a stroke inevitably contains noises, the first stage may produce wrong or inaccurate segmentation points, resulting in the wrong substroke classification in the second stage and inaccurately fitted parameters in the third stage. To overcome the noise sensitivity of the three-stage method, the segmental homogeneity feature is emphasized in this paper. We propose a novel approach, which first extracts graphical primitives from a stroke by a connected segment growing from a seed-segment and then utilizes relationships between the primitives to refine their control parameters. We have conducted experiments using real-life strokes and compared the proposed approach with others. Experimental results demonstrate that the proposed approach is effective and robust.

As one of the most common features in the man-made environments, straight lines play an important role in many applications. In this paper, we present a new framework to extract line segments from large-scale point clouds. The proposed method is fast to produce results, easy for implementation and understanding, and suitable for various point cloud data. The key idea is to segment the input point cloud into a collection of facets efficiently. These facets provide sufficient information for determining linear features in the local planar region and make line segment extraction become relatively convenient. Moreover, we introduce the concept “number of false alarms” into 3-D point cloud context to filter the false positive line segment detections. We test our approach on various types of point clouds acquired from different ways. We also compared the proposed method with several other methods and provide both quantitative and visual comparison results. The experimental results show that our algorithm is efficient and effective, and produce more accurate and complete line segments than the comparative methods. To further verify the accuracy of the line segments extracted by the proposed method, we also present a line-based registration framework, which employs these line segments on point clouds registration.

We address the problem of object recognition in computer vision. We represent each model and the scene in the form of Attributed Relational Graph. A multiple region representation is provided at each node of the scene ARG to increase the representation reliability. The process of matching the scene ARG against the stored models is facilitated by a novel method for identifying the most probable representation from among the multiple candidates. The scene and model graph matching is accomplished using probabilistic relaxation which has been modified to minimise the label clutter. The experimental results obtained on real data demonstrate promising performance of the proposed recognition system.

Depth learning has been applied in semantic segmentation and object recognition in computer vision. In this paper, we propose a high-efficiency pixel classification convolutional neural network based on encoder-decoder structure. Using depth image to enhance CNNS network make color image and depth information can be detected jointly. The experimental data shows that through the fusion of depth features representing different scales of information, the algorithm architecture can be jointly optimized and obtain more sophisticated image semantic features. Compared with similar methods, image semantic segmentation algorithm has obvious advantages.

Deep neural networks inspired by the connections among biological neurons have been highly effective in the advancement of computer vision. Recent research into recurrent neural networks has taken account of forward as well as recurrent connections in a neural network architecture. In this study, we proposed a model that mirrors the architecture of the human ventral pathway with separate layers representing brain regions connected using long-range recurrent links. CIFAR-10/100 datasets were used to assess the performance of object recognition using the proposed model and the results were compared with those obtained using state-of-the-art methods. We demonstrated that the classification accuracy increased as the number of recurrences increased. Our results suggest that the proposed neuroscience-inspired model can facilitate object recognition in computer vision and may help to elucidate neurological mechanisms in the human brain.

This study examines various algorithms for computing the convex hull of a set of n points in a d-dimensional space. Convex hulls are fundamental in computational geometry and are applied in computer graphics, pattern recognition, and computational biology. Such convex hulls can also be useful in symmetry problems. For instance, when points are arranged symmetrically, the convex hull is also likely to be symmetrically shaped, which can be useful for object recognition in computer vision or pattern recognition. The focus is primarily on two-dimensional algorithms, including well-known methods like Gift Wrapping, Graham Scan, Divide and Conquer, QuickHull, TORCH, Kirkpatrick–Sediel, and Chan’s algorithms. These algorithms vary in terms of time complexity and scalability to higher dimensions. This study is extended to three-dimensional convex hull algorithms, such as NAW, randomized insertion, and parallelized versions, such as CudaHull and CudaChain. This study aimed to elucidate the operational principles, step-by-step procedures, and comparative time complexities of each algorithm. The implementation in Python facilitates a detailed comparison of the algorithmic performance through stepwise analysis and graphical outputs. The ultimate goal is to provide insights into the strengths and weaknesses of each algorithm under various scenarios, thereby offering a comprehensive guide for practical implementation.

Hessian matrix is the square matrix of second partial derivatives of a scalar-valued function and is well known for object recognition in computer vision and medical shape analysis. Previous curvature based polyp detection algorithms generate myriad of false positives. Hessian-matrix based method, however, is more sensitive to local shape features, so easily reduce false positives. Calculation of Hessian matrix on 3D CT data and Eigen decomposition of the matrix gives three Eigen values and vectors at each voxel. Using these Eigen values, we can figure out which type of intensity structures (blob, line, and sheet-like) is on the given voxel. We focus on detecting blob-like object automatically. In the inner colonic wall structures, blob-like, line-like, and sheet-like objects represent polyps, folds and wall, respectively. In addition, to improve the performance of the algorithm, Gaussian blurring factor and shape threshold parameters are optimized. Before Hessian matrix calculation, smoothing the given region using Gaussian kernel with small deviation is necessary to enhance local intensity structures. To optimize the parameters and validate this method, we have produced anthropomorphic pig phantoms. Fourteen phantoms with 103 polyps (16 polyps <6mm, 87 >= 6mm) were used. CT scan was performed with 1mm slice thickness. Our detection algorithm found 84 polyps (81.6%) correctly. Average number of false positives is 7.9 at each CT scan. This results show that our algorithm is clinically applicable for polyp detection, because of high sensitivity and relatively low false positive detections.

For decades, the slide drilling system (SDS) has played a critical role in the area of directional drilling. Drilling in the sliding mode is much more time-consuming than drilling in the rotating mode for a SDS. Therefore, it generally takes more time to drill a curved wellbore segment than a straight segment of the same length. Based on this fact, a novel wellbore trajectory design for SDSs is proposed in this paper to reduce the total drilling time and improve economy. The basic idea of our strategy is to replace a long curved wellbore section, e.g., the build-up and drop-off sections, with a series of short circular-arc and straight-line segments in the design stage. Assuming that rotating and sliding modes are only used for straight-line and circular-arc segments, respectively, the total drilling time is reduced by increasing the average rate of penetration. Therefore, the problem lies in how to replace a long circular arc with multiple short circular arcs and straight lines to minimize the total drilling time, which is the aim of this research. In this paper, a piecewise trial strategy is proposed, where the optimized wellbore trajectory is generated by adding circular-arc and straight-line segments with equal length one by one according to the “line first” principle. This strategy converts the original optimization problem, which involves both combinatorial and parameter optimization of unknown dimension, to a much easier one, where there are only three design variables and one set of constraint equations. Due to the multimodal characteristics of the objective function, genetic algorithm (GA) is adopted to obtain the optimal solution. A great reduction of the drilling time is obtained by applying our method to two typical cases, which shows a clear potential for future field applications.

This paper presents an effective method to automatically segment and fit the edge contour curve data of a picture into straight line segments, circular arc segments or elliptical arc segments. Firstly, the curvature of each point is calculated, and the curvature change breakpoints are found to distinguish between straight lines, circular arcs and elliptical arcs; then, circular arc segments and elliptical arcs are distinguished by the change degree of curvature of adjacent points, and the automatic segmentation of contour edges is realized. Finally, the circular arc segment and elliptic arc segment are fitted by least squares method, based on which the length of the straight line, the direction angle of the circular arc, the rotation angle of the elliptic arc and other related information are calculated. The results show that our model can better identify the feature texture information of image edges.

Object recognition and reconstruction are pivot technologies both in computer vision and in machine intelligence. There are a number of techniques for object recognition, such as pattern comparison, feature matching, and boundary detection and so on, which heavily depend on the rigid depiction of projected images of the object. This consequently results in that even recognized it is still remain tough to reconstruct the target object. In this paper, we propose a novel method for object recognition and reconstruction based on shape knowledge, which is constructed as a repository of three-dimensional shapes to reinforce the system intelligence. The method employs a feature matching algorithm to find the best matching object in the knowledge base and to implement the reconstruction of the object recognized. Preliminary experiment results show that the proposed method can effectively compensate the inadequacy of information in shape reconstruction and deliver the satisfied three-dimensional information for the recognized object. This is rather helpful in image based object recognition and reconstruction where the three-dimensional topological information of the object is almost empty.

Point-based matching methods usually hold limitation in dealing with low texture scenes. In this paper, a robust affi neinvariant lines matching method is proposed. The method commences with line segments extraction. All the extracted line segments are grouped into salient lines and general lines. Accordingly, the matching procedure includes salient lines matching and general lines matching. In salient lines matching, affi ne invariants are calculated and the matched salient line correspondences are the basis of the general lines matching. Each general line is clustered into a matched salient line according to a certain rule. Taking each salient line as the root, together with all the general lines clustered to it, a control network is constructed. Finally, the general lines matching procedure is performed between the two subnetworks whose roots are correspondences. Experimental results show that our proposed method can successfully process local distortion and improve the matching performance in low texture areas.

The intelligent campus surveillance system is beneficial to improve safety in school. Abnormal behavior recognition, a field of action recognition in computer vision, plays an essential role in intelligent surveillance systems. Computer vision has been actively applied to action recognition systems based on Convolutional Neural Networks (CNNs). However, capturing sufficient motion sequence features from videos remains a significant challenge in action recognition. This work explores the challenges of video-based abnormal behavior recognition on campus. In addition, a novel framework is established on long-range temporal video structure modeling and a global sparse uniform sampling strategy that divides a video into three segments of identical durations and uniformly samples each snippet. The proposed method incorporates a consensus of three temporal segment transformers (TST) that globally connects patches and computes self-attention with joint spatiotemporal factorization. The proposed model is developed on the newly created campus abnormal behavior recognition (CABR50) dataset, which contains 50 human abnormal action classes with an average of over 700 clips per class. Experiments show that it is feasible to implement abnormal behavior recognition on campus and that the proposed method is competitive with other peer video recognition in terms of Top-1 and Top-5 recognition accuracy. The results suggest that TST-L+ can improve campus abnormal behavior recognition, corresponding to Top-1 and Top-5 accuracy results of 83.57% and 97.16%, respectively.

The role of invariant line junctions in object and visual word recognition

The field of computer vision has undergone rapid development. Starting from recognition tasks such as classification, detection, and segmentation, the focus of visual analysis has gradually shifted towards learning spatiotemporal information. This thesis presents research on spatiotemporal learning, with a particular emphasis on motion estimation and visual recognition. First, we address the problem of video object tracking. Previous methods have primarily re-lied on learning improved appearance representations, while the spatiotemporal relationships of individual objects have been underexplored. We propose leveraging optical flow features to achieve higher generalization in semi-supervised video object segmentation, directly incorporating these features into both the target representation and the decoder network. Our experiments and analysis show that enriching feature representations with spatiotemporal information improves segmentation quality and generalization capability. Next, we investigate spatiotemporal learning in 3D for motion estimation, specifically scene flow estimation. Scene flow estimation as an important research topic in 3D computer vision is crucial for applications such as robotics, autonomous driving, embodied navigation, and tracking. We investigate the problem in different perspectives: 1. What is the best formulation for solving the problem and how to learn a better spatiotemporal feature representation? 2. Can we introduce uncertainty estimation to the task, which is of crucial importance for safety-critical downstream tasks? 3. How to scale the estimation to large-scale data, e.g., autonomous scenes, and leverage the temporal information without introducing much computation overheads? To answer these questions, we explore the use of transformers for improved feature representation, diffusion models for uncertainty estimation, and efficient feature learning methods for multi-frame, large-scale autonomous driving scenarios. Finally, we extend our research to joint visual segmentation, tracking, and open-vocabulary recognition in LiDAR sequences, particularly for autonomous scenes. In such environments, precise segmentation, tracking, and recognition of objects are essential for downstream analysis and control. Current human-annotated open-source datasets allow for reasonable tracking of traffic participants such as cars and pedestrians. However, we aim to advance beyond this towards segmenting and tracking any object in LiDAR data. To this end, we propose a pseudo-labeling engine that leverages the 2D visual foundation model SAM v2 and the vision-language model CLIP to automatically label LiDAR streams. We further introduce the SAL-4D model, capable of segmenting, tracking, and recognizing any object in a zero-shot manner. In summary, we explore the learning of spatiotemporal information in both 2D image and 3D point cloud domains. In the image domain, we demonstrate that spatiotemporal information improves video object segmentation quality and generalization. In the 3D point cloud domain, we show that spatiotemporal learning enables more accurate motion estimation and facilitates the first method for zero-shot segmentation, tracking, and open-vocabulary recognition of arbitrary objects.