A new performance measure and evaluation benchmark for road detection algorithms

By J. Fritsch, Tobias Kühnl, Andreas Geiger. 2013

687 citations recorded by the source corpus.

Subfields: Automotive Engineering, Computer Vision and Pattern Recognition, Evaluation & Benchmarks

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Automotive Engineering

In Computer Vision and Pattern Recognition

In Evaluation & Benchmarks

Citations in the corpus

CCNet: Criss-Cross Attention for Semantic Segmentation (2018, background): “It has been extensively and actively studied in many recent works and is also critical for various challenging and meaningful applications such as autonomous driving [14], augmented reality [1], and image editing [13].”
Attention to Scale: Scale-Aware Semantic Image Segmentation (2015, background): “Successful image segmentation techniques could facilitate a large group of applications such as image editing [17], augmented reality [3] and self-driving vehicles [22].”
BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning (2018, neutral): “Caltech Lanes Dataset [4] - 1,224 4 Road Marking Dataset [32] - 1,443 29 KITTI-ROAD [14] 289 579 VPGNet [18] 14,783 21,097 -”
Understanding Convolution for Semantic Segmentation (2017, methodology): “We report our experiments and results on three challenging semantic segmentation datasets: Cityscapes [5], KITTI dataset [10] for road estimation, and PASCAL VOC2012 [8].”
Line-CNN: End-to-End Traffic Line Detection With Line Proposal Unit (2020, background): “For example, a fundamental task in automatic driving is vehicle navigation or drivable lane recognition, and it is tackled by existing researches from two aspects, namely road region segmentation1 [1]–[5] and traffic line detection [6]–[11] (see Fig.”
Testing of Advanced Driver Assistance Towards Automated Driving: A Survey and Taxonomy on Existing Approaches and Open Questions (2015, background): “Using a reference sensor often requires to map two different physical measurement principles and thus models as well. and hence perform an abstraction of reality themselves.”
SNE-RoadSeg: Incorporating Surface Normal Information into Semantic Segmentation for Accurate Freespace Detection (2020, methodology): “– The KITTI road dataset [15]: this dataset provides real-world RGB-D vision data.”
Recent progress in semantic image segmentation (2018, methodology): “KITTI dataset (Fritsch et al. 2013; Menze and Geiger 2015), as another dataset for autonomous driving, captured by driving around mid-size city of Karlsruhe, on highways, and in rural areas.”
BDD100K: A Diverse Driving Video Database with Scalable Annotation Tooling (2018, neutral): “Caltech Lanes Dataset [2] - 1,224 4 1 1 2 Road Marking Dataset [21] - 1,443 29 2 3 10 KITTI-ROAD [11] 289 579 1 1 2 VPGNet [13] 14,783 21,097 4 2 17 Ours 70,000 100,000 100,000 6 3 11 Table 2: Comparisons with other lane marking datasets.”
Fast LIDAR-based road detection using fully convolutional neural networks (2017, background): “A top-view representation is, in our opinion, more appropriate than a camera perspective representation given that both path planning and vehicle control are executed in this 2D world [2].”
CGNet: A Light-Weight Context Guided Network for Semantic Segmentation (2018, background): “SEMANTIC segmentation has been an vital component for scene understanding, and plays a crucial role in many applications such as image editing [1], autonomous driving [2], and virtual reality [3].”
MultiNet: Real-time Joint Semantic Reasoning for Autonomous Driving (2016, methodology): “We use the road benchmark of [12] to evaluate the performance of our semantic segmentation decoder and the object detection benchmark [15] for the detection decoder.”
A constant-time SLAM back-end in the continuum between global mapping and submapping: application to visual stereo SLAM (2016, methodology): “2014) (referred as MAPIR dataset from now on), and one of the road datasets from the KITTI Vision Benchmark Suite (Geiger et al. 2012; Fritsch et al. 2013).”
Find your own way: Weakly-supervised segmentation of path proposals for urban autonomy (2016, methodology): “For the comparison using the KITTI Road benchmark presented in Section V-B.1, we trained an additional SegNet model on only the training images provided for the Ego-Lane Estimation Evaluation.”
Computer Vision for Autonomous Vehicles: Problems, Datasets and State-of-the-Art (2017, methodology): “The KITTI benchmark was extended by Fritsch et al. (2013) to the task of road/lane detection.”
Spatial As Deep: Spatial CNN for Traffic Scene Understanding (2017, background): “KITTI (Fritsch, Kuhnl, and Geiger 2013) and CamVid (Brostow et al. 2008) contains pixel level annotations for lane/lane markings, but have merely hundreds of images, too small for deep learning methods.”
Deep Quaternion Networks (2017, methodology): “EXPERIMENTAL RESULTS Our experiments covered image classification using both the CIFAR-10 and CIFAR-100 benchmarks [24] and image segmentation using the KITTI Road Estimation benchmark [25].”