Procedia Computer Science · 2020 · 20 citations · 19 references
ComputingAutonomous SystemsComputer ScienceAutonomous VehiclesComputer VisionMachine LearningDepth EstimationObject DetectionObject RecognitionObstacle DetectionScene UnderstandingStereo VisionAutonomous Vehicle NavigationConvolutional Neural Network DetectionConvolutional Neural NetworksObject ClassificationObject Detection In Autonomous DrivingStereo Vision NavigationStereo Vision Obstacle DetectionVehicle Detection
Autonomous vehicles with various levels of autonomy are becoming popular in developed countries due to their effectiveness in reducing the fatalities caused by road accidents. A developing country like India with the second largest population in the world, creates unique road scenarios for an autonomous car which requires a lot of testing and fine tuning before implementation. This leads to the importance of datasets providing information about various traffic situations in India. For planning its path ahead, autonomous vehicles have to detect, classify and estimate the depth of obstacles that they encounter on roads. The purpose of this paper is to provide a dataset for object classification, detection and stereo vision corresponding to Indian roads which can serve as a platform for developing effective algorithms for autonomous cars in Indian roads. In this work, we benchmarked the object classification by using confusion matrix obtained from various deep learning models, evaluated detection using Faster R-CNN and compared depth estimation processed by Realsense stereo camera by applying convolutional neural network based algorithms.
19
ImageNet: A large-scale hierarchical image database
Jia Deng, Wei Dong, Richard Socher et al. · 2009 IEEE Conference on Computer Vision and Pattern Recognition · 2009 · 61.8K citations
Densely Connected Convolutional Networks
Gao Huang, Zhuang Liu, Laurens van der Maaten et al. · 2017 · 44.7K citations
Rethinking the Inception Architecture for Computer Vision
Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe et al. · 2016 · 30.9K citations
The Pascal Visual Object Classes (VOC) Challenge
Mark Everingham, Luc Van Gool, Christopher K. I. Williams et al. · International Journal of Computer Vision · 2009 · 19.5K citations · Full text