Key Points Estimation and Point Instance Segmentation Approach for Lane Detection

Abstract

State-of-the-art lane detection methods achieve successful performance. Despite their advantages, these methods have critical deficiencies such as the limited number of detectable lanes and high false positive. In especial, high false positive can cause wrong and dangerous control. In this paper, we propose a novel lane detection method for the arbitrary number of lanes using the deep learning method, which has the lower number of false positives than other recent lane detection methods. The architecture of the proposed method has the shared feature extraction layers and several branches for detection and embedding to cluster lanes. The proposed method can generate exact points on the lanes, and we cast a clustering problem for the generated points as a point cloud instance segmentation problem. The proposed method is more compact because it generates fewer points than the original image pixel size. Our proposed post processing method eliminates outliers successfully and increases the performance notably. Whole proposed framework achieves competitive results on the tuSimple dataset. Our code is available at https://github. com/koyeongmin/PINet

Focus on Local: Detecting Lane Marker from Bottom Up via Key Point

“…Quantitative results. To verify the effectiveness of our proposed method, we compared it with state-of-the-art algorithms based on either segmentation or object detection, including SCNN [12], LaneNet(+H-Net) [10], EL-GAN [4], PointLaneNet [2], FastDraw [14], ENet-SAD [5], ERFNet-E2E [20], SIM-CycleGAN+ERFNet [9], UFNet [16] and PINet [6].…”

“…Accuracy(%) FP FN SCNN [12] 96.53 0.0617 0.0180 LaneNet(+H-Net) [10] 96.40 0.0780 0.0244 EL-GAN [4] 96.39 0.0412 0.0336 PointLaneNet [2] 96.34 0.0467 0.0518 FastDraw [14] 95.2 0.0760 0.0450 ENet-SAD [5] 96.64 0.0602 0.0205 ERFNet-E2E [20] 96.02 0.0321 0.0428 PINet(4H) [6] 96.75 0.0310 0.0250 FOLOLane(ours) 96.92 0.0447 0.0228 Table 3. Performance of different methods on TuSimple testing set.…”

“…[19] proposed the use of neural architecture search(NAS) to find a better backbone and a point blending based post processing to further improve the performance of lane marker detection task. [6] proposed to train a CNN to predict the existence, position and feature embedding of lane markers in an image. A lane marker instance was clustered based on the trained feature embedding.…”

“…The weight λ for loss function in Eq. [6] was set as 0.02. For optimization, we used Adam optimizer and poly learning rate schedule with an initial learning rate of 0.001.…”

Accurate and Lightweight RailNet for Real-Time Rail Line Detection

“…With the bottom edge of the feature map set to the x-axis after inverse fluoroscopic transformation, the distribution of pixels in the vertical direction of the image for each abscissa on the x-axis is statistically derived using a histogram [26]. At this time, because most feature pixels belong to the tracks, there will be two apparent peaks near the abscissa of the rail lines on the left and right sides [27]. The coordinates of these two peaks are the starting points of sliding window detection.…”