A survey of Hough Transform Mukhopadhyay, Priyanka; Chaudhuri, Bidyut B.
Pattern recognition,
03/2015, Volume:
48, Issue:
3
Journal Article
Peer reviewed
In 1962 Hough earned the patent for a method 1, popularly called Hough Transform (HT) that efficiently identifies lines in images. It is an important tool even after the golden jubilee year of ...existence, as evidenced by more than 2500 research papers dealing with its variants, generalizations, properties and applications in diverse fields. The current paper is a survey of HT and its variants, their limitations and the modifications made to overcome them, the implementation issues in software and hardware, and applications in various fields. Our survey, along with more than 200 references, will help the researchers and students to get a comprehensive view on HT and guide them in applying it properly to their problems of interest.
•A survey of Hough Transform (HT) has been done.•The main variants of HT and its formulations have been described.•The hardware and software implementations of HT have been described.•HT has many applications in diverse fields. Out of them some applications in some selected fields have been mentioned.
The Circle Hough Transform (CHT) is one of the popular circle detection algorithm in image processing and machine vision application, favored for its tolerance to noise. Nevertheless, it involves ...huge computation and excessive memory requirements. Because of its drawbacks, various modifications have been suggested to increase its performances. In this paper, we present a new modification of the CHT method developed for an automatic biometric iris recognition system. The novelty of this method resides on the use of the incremental property in order to reduce the resources requirement and the parallel property for decreasing the computation time. The incremental property is obtained using the approximation of the used trigonometric functions, while the parallel property is achieved by calculating, at the same time, several point coordinates of the circle. The software implementation and the validation have been done in C++ and MATLAB on real images. The errors analysis and the performances of the proposed method against the basic CHT method are presented in this paper.
The paper introduces Hough forests, which are random forests adapted to perform a generalized Hough transform in an efficient way. Compared to previous Hough-based systems such as implicit shape ...models, Hough forests improve the performance of the generalized Hough transform for object detection on a categorical level. At the same time, their flexibility permits extensions of the Hough transform to new domains such as object tracking and action recognition. Hough forests can be regarded as task-adapted codebooks of local appearance that allow fast supervised training and fast matching at test time. They achieve high detection accuracy since the entries of such codebooks are optimized to cast Hough votes with small variance and since their efficiency permits dense sampling of local image patches or video cuboids during detection. The efficacy of Hough forests for a set of computer vision tasks is validated through experiments on a large set of publicly available benchmark data sets and comparisons with the state-of-the-art.
The task of lane detection has garnered considerable attention in the field of autonomous driving due to its complexity. Lanes can present difficulties for detection, as they can be narrow, ...fragmented, and often obscured by heavy traffic. However, it has been observed that the lanes have a geometrical structure that resembles a straight line, leading to improved lane detection results when utilizing this characteristic. To address this challenge, we propose a hierarchical Deep Hough Transform (DHT) approach that combines all lane features in an image into the Hough parameter space. Additionally, we refine the point selection method and incorporate a Dynamic Convolution Module to effectively differentiate between lanes in the original image. Our network architecture comprises a backbone network, either a ResNet or Pyramid Vision Transformer, a Feature Pyramid Network as the neck to extract multi-scale features, and a hierarchical DHT-based feature aggregation head to accurately segment each lane. By utilizing the lane features in the Hough parameter space, the network learns dynamic convolution kernel parameters corresponding to each lane, allowing the Dynamic Convolution Module to effectively differentiate between lane features. Subsequently, the lane features are fed into the feature decoder, which predicts the final position of the lane. Our proposed network structure demonstrates improved performance in detecting heavily occluded or worn lane images, as evidenced by our extensive experimental results, which show that our method outperforms or is on par with state-of-the-art techniques.
Display omitted
•Propose a new way to detect lanes by using their straight-line shape prior.•Combine lane features to Hough points by a Deep Hough Transform module.•Incorporating a Dynamic Convolution Module to differentiate between lanes.•Works well even with hard images and is as good as or better than other ways.
•Curvature radius is adopted to improve the H-transform for circle detection.•Curvature pre-estimation avoids senseless accumulation operation, work faster.•The CACD is capable to detect circles of ...different radius in complex scene.•“Statistic deviation” is defined to measure the saliency of circle center.
Conventional Hough based circle detection methods are robust, but for computers in last century, it is to slow and memory demanding. With the rapid development of computer hardware, Hough transform is acceptable now. Improvement on Hough based circle detection is valuable. In this paper, we present a novel curvature aided Hough transform for circle detection (CACD) algorithm, which estimates the circle radius from curvature. Curvature pre-estimation is capable to avoid both accumulating operations of all the points and interruption between different scales, which result in faster and more precise circle detection. Compared to the conventional Hough-based algorithm for circle detection, the algorithm is more practical and less time consuming. Its time taking is about 1/8 of that of conventional algorithm. Test results on traffic sign images shown that The CACD gets an AUC (Area Under Curve) of 0.9125. The CACD is capable to detect circles of different radius in complex scene.
Deep Hough Transform for Semantic Line Detection Zhao, Kai; Han, Qi; Zhang, Chang-Bin ...
IEEE transactions on pattern analysis and machine intelligence,
09/2022, Volume:
44, Issue:
9
Journal Article
Peer reviewed
Open access
We focus on a fundamental task of detecting meaningful line structures, a.k.a. , semantic line, in natural scenes. Many previous methods regard this problem as a special case of object detection and ...adjust existing object detectors for semantic line detection. However, these methods neglect the inherent characteristics of lines, leading to sub-optimal performance. Lines enjoy much simpler geometric property than complex objects and thus can be compactly parameterized by a few arguments. To better exploit the property of lines, in this paper, we incorporate the classical Hough transform technique into deeply learned representations and propose a one-shot end-to-end learning framework for line detection. By parameterizing lines with slopes and biases, we perform Hough transform to translate deep representations into the parametric domain, in which we perform line detection. Specifically, we aggregate features along candidate lines on the feature map plane and then assign the aggregated features to corresponding locations in the parametric domain. Consequently, the problem of detecting semantic lines in the spatial domain is transformed into spotting individual points in the parametric domain, making the post-processing steps, i.e., non-maximal suppression, more efficient. Furthermore, our method makes it easy to extract contextual line features that are critical for accurate line detection. In addition to the proposed method, we design an evaluation metric to assess the quality of line detection and construct a large scale dataset for the line detection task. Experimental results on our proposed dataset and another public dataset demonstrate the advantages of our method over previous state-of-the-art alternatives. The dataset and source code is available at https://mmcheng.net/dhtline/ .
•Intelligent machine vision inspection method based on deep learning.•Selection of Region of Interest with background removal based on Hough transform.•Inverted residual block is introduced to ...improve computational efficiency.•Effectiveness is experimentally validated with bottle inspection.
Machine vision based product inspection methods have been widely investigated to improve product quality and reduce labour costs. Recent advancement in deep learning provides advanced analytics tools with high inspection accuracy and robustness. However, the construction of deep learning model is typically computationally expensive, which may not match the requirements for quick inspection. Therefore, this paper presents a new deep learning based machine vision inspection method to identify and classify defective product without loss of accuracy. In specific, Gaussian filter is first performed on the acquired image to limit random noise. Then, a region of interest (ROI) extracting project is conducted based on Hough transform to remove the unrelated background, thereby offloading the computational burden of the subsequent identification process. The construction of the identification module is based on convolutional neural network, whereas inverted residual block is introduced as the basic block to strike a good balance between identification accuracy and computational efficiency. The superior inspection performance is obtained using the proposed method with a large amount of dataset which consists of defective and defect-free bottle images.
•Automatic measurement of particle size distribution from micrographs.•The proposed algorithm is mainly based on local adaptive Canny edge detection and modified circular Hough transform.•The ...robustness and reliability of the algorithm were verified by several micrographs with different complexity.
To obtain size distribution of nanoparticles, scanning electron microscope (SEM) and transmission electron microscopy (TEM) have been widely adopted, but manual measurement of statistical size distributions from the SEM or TEM images is time-consuming and labor-intensive. Therefore, automatic detection methods are desirable. This paper proposes an automatic image processing algorithm which is mainly based on local adaptive Canny edge detection and modified circular Hough transform. The proposed algorithm can utilize the local thresholds to detect particles from the images with different degrees of complexity. Compared with the results produced by applying global thresholds, our algorithm performs much better. The robustness and reliability of this method have been verified by comparing its results with manual measurement, and an excellent agreement has been found. The proposed method can accurately recognize the particles with high efficiency.
Many contact-sensor-based methods for structural damage detection have been developed. However, these methods have difficulty compensating for environmental effects, such as variation or changes in ...temperature and humidity, which may lead to false alarms. In order to partially overcome these disadvantages, vision-based approaches have been developed to detect corrosions, cracks, delamination, and voids. However, there are few such approaches for loosened bolts. Therefore, we propose a novel vision-based detection method. Target images of loosened bolts were taken by a smartphone camera. From the images, simple damage-sensitive features, such as the horizontal and vertical lengths of the bolt head, were calculated automatically using the Hough transform and other image processing techniques. A linear support vector machine was trained with the aforementioned features, thereby building a robust classifier capable of automatically differentiating tight bolts from loose bolts. Leave-one-out cross-validation was adapted to analyze the performance of the proposed algorithm. The results highlight the excellent performance of the proposed approach to detecting loosened bolts, and that it can operate in quasi-real-time.
•An automated computer-vision method for detecting loosened bolts is proposed.•Advanced image processing, feature extraction techniques, and LSVM are integrated.•The proposed method shows high computational efficiency with simple features.•The method shows robust performance within the limited range of angle and distance.
The high velocity of the re-entry object causes its surface to be enveloped with a plasma sheath. In the process of target detection of re-entry objects, the plasma sheath with fluid characteristics ...results in multiple reflected signals in the radar echo. Multiple targets appear in the 1-D range profile following pulse compression processing of a multicomponent echo signal. We refer to targets different from the real target as interference targets. The appearance of interference targets seriously affects the radar detection of re-entry objects, resulting in positioning failure or even tracking loss. In this article, by establishing the physical model of radar echo with multiple reference points and multiple velocity parameters of the re-entry object under plasma sheath, the multitarget phenomenon of the re-entry target echo signal on the 1-D range profile is simulated. A target detection method based on Doppler frequency compensation and nonuniform plasma sheath reflection model is proposed, which can effectively suppress false targets and realize reliable detection of targets under plasma sheath. The feasibility of detecting a target enveloped by a plasma sheath is verified by simulation, laying the foundation for the precise detection and tracking of targets.