Crosswalk Detection Based on MSER and ERANSAC

Abstract

Crosswalks detection and location in traffic scenes plays an important role in the Intelligent Transportation Management System (ITMS). In this paper, we propose a new novel and robust approach for the detection and location of crosswalks, which is based on Maximally Stable Extremal Regions (MSER) and extended Random Sample Consensus (ERANSAC). Specially, first, the method with temporal median of background extraction is applied to traffic monitoring videos so that the foreground has a less disturbance for crosswalks detection and location. Second, we use a method of MSER to extract crosswalk features in the image. Last, we invent the ERANSAC to pick out crosswalk features extracted by MSER to detect and locate crosswalk and indicate the position of crosswalk in the image. Compared to the existing detection methods, the proposed method based on MSER can efficiently extract crosswalk regions under various illumination conditions, which can avoid the selection of thresholds according to the current environment situation and greatly improve the system flexibility and robustness. The ERANSAC can determine the distance between candidate samples and get the principle components by the way of eliminating the non-crosswalk regions. Promising experimental results have demonstrated that the proposed method has a high detection rate at extremely false alarm and is robust to the different crosswalk angle and various illuminations.

From Pedestrian Detection to Crosswalk Estimation: An EM Algorithm and Analysis on Diverse Datasets

“…Past approaches to detecting crosswalks have been primarily based on camera images of the static scene. Such methods include figure-ground segmentation (Coughlan & Shen, 2006), edge direction and cross-ratio analysis (Suzuki et al, 2010), Canny edge detection and Hough line parameter estimation (Tian et al, 2021), MSER and ERANSAC (Zhai et al, 2015), laser scanning (Hernndez et al, 2015), monocular image deep learning to classify presence of crosswalk in overall scene (Tmen & Ergen, 2020), PCA-based road segmentation and crosswalk detection from a LiDAR point cloud (Riveiro et al, 2015), and image classification using deep learning over massive instances from satellite imagery (Berriel et al, 2017).…”

Traffic Scenarios and Vision Use Cases for the Visually Impaired

“…For Crosswalk Detection, [31] proposes to extract according regions under different illuminations by means of MSER and to eliminate false candidates afterwards. The fact that crosswalks have a horizontal structure from driver perspective is used by [32] and [33].…”

Detection of Damaged Stop Lines on Public Roads by Focusing on Piece Distribution of Paired Edges

“…In general, determining characteristic features of the targets is important for detecting road marks. For example, when detecting crosswalks [10][11][12][13][14], the rectangular shape of a white band with clear side edges and the regularly repeating distribution of the white bands are typical features. Because these features are relatively complex, they are key for detecting crosswalks.…”