EFFICIENT LINE DETECTION METHOD BASED ON 2D CONVOLUTION FILTER

The article proposes an efficient line detection method using a 2D convolution filter. The proposed method was compared with the Hough transform, the most popular method of straight lines detection. The developed method is suitable for local detection of straight lines with a slope from -45˚ to 45˚. Also, it can be used for curve detection which shape is approximated with the short straight sections. The new method is characterized by a constant computational cost regardless of the number of set pixels. The convolution is performed using the logical conjunction and sum operations. Moreover, design of the developed filter and the method of filtration allows for parallelization. Due to constant computation cost, the new method is suitable for implementation in the hardware structure of real-time image processing systems.

Lane Line Extraction in Raining Weather Images by Ridge Edge Detection with Improved MSR and Hessian Matrix

To accurately detect lane lines in road traffic images at raining weather, a edge detection based method is studied, which mainly includes four algorithms. (1) Firstly an image is enhanced by an improved Retinex algorithm; (2) Then, an algorithm based on the Hessian matrix is applied to strengthen lane lines; (3) To extract the feature points of a lane line, a ridge edge detection algorithm based on five line detection in four directions is proposed, in which, in light on the possible positions of lane lines in the image, it detects the maximum gray level points in the local area of the detecting point within the pre-set valid detection region; and (4) After the noise removal based on the minimum circumscribed rectangles, the candidate points of lane lines are connected as segments, and for the gap filling between segments, in order to make connection correctly, the algorithm makes the filling in two steps, short gap and long gap fillings, and the long gap filling is made on the combination of segment angle difference and gap distance and gap angle. By testing hundreds of images of the lane lines at raining weather and by comparing several traditional image enhancement and segmentation algorithms, the new method of the lane line detection can produce the satisfactory results.

Around-View-Monitoring-Based Automatic Parking System Using Parking Line Detection

This paper introduces an automatic parking method using an around view monitoring system. In this method, parking lines are extracted from the camera images, and a route to a targeted parking slot is created. The vehicle then tracks this route to park. The proposed method extracts lines from images using a line filter and a Hough transform, and it uses a convolutional neural network to robustly extract parking lines from the environment. In addition, a parking path consisting of curved and straight sections is created and used to control the vehicle. Perpendicular, angle, and parallel parking paths can be created; however, parking control is applied according to the shape of each parking slot. The results of our experiments confirm that the proposed method has an average offset of 10.3 cm and an average heading angle error of 0.94°.

B-Line Detection and Localization in Lung Ultrasound Videos Using Spatiotemporal Attention

The presence of B-line artefacts, the main artefact reflecting lung abnormalities in dengue patients, is often assessed using lung ultrasound (LUS) imaging. Inspired by human visual attention that enables us to process videos efficiently by paying attention to where and when it is required, we propose a spatiotemporal attention mechanism for B-line detection in LUS videos. The spatial attention allows the model to focus on the most task relevant parts of the image by learning a saliency map. The temporal attention generates an attention score for each attended frame to identify the most relevant frames from an input video. Our model not only identifies videos where B-lines show, but also localizes, within those videos, B-line related features both spatially and temporally, despite being trained in a weakly-supervised manner. We evaluate our approach on a LUS video dataset collected from severe dengue patients in a resource-limited hospital, assessing the B-line detection rate and the model’s ability to localize discriminative B-line regions spatially and B-line frames temporally. Experimental results demonstrate the efficacy of our approach for classifying B-line videos with an F1 score of up to 83.2% and localizing the most salient B-line regions both spatially and temporally with a correlation coefficient of 0.67 and an IoU of 69.7%, respectively.