CLRNet: Cross Layer Refinement Network for Lane Detection

Abstract

Scope of Reproducibility -The following work is a reproducibility report for CLRNet: Cross Layer Refinement Network for Lane Detection [1]. The basic code was made available by the author at this https url. The paper proposes a novel Cross Layer Refinement Network to utilize both high and low level features for lane detection. The authors assert that the proposed technique sets the new state-of-the-art on three lane-detection benchmarks.Methodology -The proposed model employs a two-stage approach to lane detection. Initially, coarse lane detection is achieved through the extraction of high-level semantic features. This is followed by refinement of the output based on low-level features, aimed at enhancing the localization accuracy of the model. The authors' code was used to benchmark the claims. Some further experiments were investigated thereafter. Kaggle, a free-to-use platform for deep learning experiments, was used to train these models. We have reproduced the code base in Pytorch Lightning and found consistent results across the board. Results -The central claims presented by the authors were subject to reproduction and verification. The validity of the claims was evaluated using two out of the three datasets referenced in the original paper. The results obtained from the CULane dataset showed close agreement with the original findings, with deviations of less than 1% on most of the metrics. This suggests the reproducibility and reliability of the claims made by the authors. However, in experiments on the TuSimple dataset, substantial disparities were noted between our results and those reported in the original paper. The probable causes of these inconsistencies are discussed in the study.What was easy -Obtaining the proposed results on the CULane dataset was readily achievable. The codebase provided by the authors was well-documented and functional. Owing to the modularity of the code, further experiments could be run with minimal changes overall. Porting the codebase to PyTorch Lightning was also facile.What was difficult -Using the LLAMAS dataset proved to be a challenge for resource constrained students owing to its size. We were eventually unable to set up experimentation on that dataset. Limited computational resources proved to be a challenge even for the other datasets, with each epoch taking over 2 hours on CULane. Total training time

BSNet: Lane Detection via Draw B-spline Curves Nearby

“…Its speed is much faster than Line-CNN. CLR-Net [34] proposes a refinement mechanism to utilize lowlevel and high-level features and proposes ROIGather to gather global context. Line-anchor-based methods have high accuracy, but they can't predict nearly horizon lanes due to the inherent shortcoming of line anchors.…”

“…More specifically, the globality of lane representation is very beneficial in predicting holistic lanes since it makes completing invisible parts efficient. Line-anchor-based methods [10,24,26,34] predict small offsets, then the globality obtained from line anchor priors doesn't be broken. Curve-based methods' lane representations are holistic curves and have natural globality.…”

CurveFormer: 3D Lane Detection by Curve Propagation with Curve Queries and Attention

“…Lane regression algorithms can be grouped into key points estimation [5], [6], anchor-based regression [7]- [11] and row-wise regression [12], [27]. PINet [5] combines key points estimation and instance segmentation, and GANet [6] represents lanes as a set of key points which are only related to the start point.…”

“…PointLaneNet [7] and CurveLane-NAS [8] separate images into non-overlapping grids and regress lanes based on vertical anchors. Line-CNN [9] and LaneATT [10] regress lanes on the pre-defined ray-anchors, while CLRNet [11] dynamically refines the start point and angle of ray-anchors through pyramidal features. Ultra-Fast [12] introduces a novel row-wise classification method with remarkable speed.…”

SCA: Search-Based Computing Hardware Architecture with Precision Scalable and Computation Reconfigurable Scheme

“…Computer-vision-based applications, such as image classification and object detection, are widely used in industrial detection, automatic driving, and robot brains. With the development of deep learning theory, more and more artificial intelligent (AI) vision applications based on convolution neural networks have achieved significant improvements in the corresponding metrics compared with traditional methods, including improved accuracy and mean average precision (mAP) [ 1 , 2 , 3 , 4 , 5 , 6 , 7 , 8 ]. In recent years, AI computer vision applications have progressively penetrated into daily life in areas such as face recognition, smart homes and automatic driving.…”