ETH

ETH Pedestrian

ImagesVideosUnknownIntroduced 2007-01-01

ETH is a dataset for pedestrian detection. The testing set contains 1,804 images in three video clips. The dataset is captured from a stereo rig mounted on car, with a resolution of 640 x 480 (bayered), and a framerate of 13--14 FPS.

Source: Scale-aware Fast R-CNN for Pedestrian Detection Image Source: https://medium.com/@zhenqinghu/pedestrian-detection-on-eth-data-set-with-faster-r-cnn-19d0a906f1d3

Benchmarks

Trajectory Prediction/Avg AMD/AMV 8/12

Related Benchmarks

ETH (trained on 3DMatch)/3D Point Cloud Interpolation/Feature Matching Recall ETH (trained on 3DMatch)/3D Point Cloud Interpolation/Recall (30cm, 5 degrees)ETH (trained on 3DMatch)/Point Cloud Registration/Feature Matching Recall ETH (trained on 3DMatch)/Point Cloud Registration/Recall (30cm, 5 degrees)ETH BIWI Walking Pedestrians dataset/Trajectory Prediction/ADE-8/12 ETH-XGaze/Gaze Estimation/Angular Error ETH/UCY/Trajectory Prediction/ADE-8/12 ETH/UCY/Trajectory Prediction/FDE-8/12 ETH3D/3D/Delta < 1.25 ETH3D/3D/absolute relative error ETH3D/Dense Pixel Correspondence Estimation/AEPE (rate=3)ETH3D/Dense Pixel Correspondence Estimation/AEPE (rate=5)ETH3D/Depth Estimation/Delta < 1.25 ETH3D/Depth Estimation/absolute relative error ETH3D/Multi-View 3D Reconstruction/F1 score Ethanol/Atomistic Description/MAE Ethanol/Formation Energy/MAE EthanolConcentration/Time Series Classification/Accuracy Ethics/Ethics/Accuracy Ethics (per ethics)/Ethics/Accuracy Ethos Binary/Abuse Detection/Classification Accuracy Ethos Binary/Abuse Detection/F1-score Ethos Binary/Abuse Detection/Precision Ethos Binary/Hate Speech Detection/Classification Accuracy Ethos Binary/Hate Speech Detection/F1-score Ethos Binary/Hate Speech Detection/Precision Ethos MultiLabel/Abuse Detection/Hamming Loss Ethos MultiLabel/Hate Speech Detection/Hamming Loss