Fisheye8K_all_including_train&test_1.zip

網址: https://scidm.nchc.org.tw/dataset/fisheye8k/resource/9461c310-d2b2-45b6-afa7-0e2b2169f74c/nchcproxy

  • this the all dataset files including train/ and test/ folders.

Description

With the advance of AI, road object detection has been a prominent topic in computer vision, mostly using perspective cameras. Fisheye lens provides omnidirectional wide coverage for using fewer cameras to monitor road intersections, however with view distortions. To our knowledge, there is no existing open dataset prepared for traffic surveillance on fisheye cameras. This paper introduces an open FishEye8K benchmark dataset for road object detection tasks, which comprises 157K bounding boxes across five classes (Pedestrian, Bike, Car, Bus, and Truck). In addition, we present benchmark results of State-of-The-Art (SoTA) models, including variations of YOLOv5, YOLOR, YOLO7, and YOLOv8. The dataset comprises 8,000 images recorded in 22 videos using 18 fisheye cameras for traffic monitoring in Hsinchu, Taiwan, at resolutions of 1080x1080 and 1280x1280. The data annotation and validation process were arduous and time-consuming, due to the ultra-wide panoramic and hemispherical fisheye camera images with large distortion and numerous road participants, particularly people riding scooters. To avoid bias, frames from a particular camera were assigned to either the training or test sets, maintaining a ratio of about 70:30 for both the number of images and bounding boxes in each class. Experimental results show that YOLOv8 and YOLOR outperform on input sizes 640x640 and 1280x1280, respectively. The dataset will be available on the GitHub (https://github.com/MoyoG/FishEye8K) with PASCAL VOC, MS COCO, and YOLO annotation formats. The FishEye8K benchmark will provide significant contributions to the fisheye video analytics and smart city applications.

@InProceedings{Munk_2023_CVPR_Workshops, author = {Munkhjargal Gochoo and Munkh-Erdene Otgonbold and Erkhembayar Ganbold and Hsieh, Jun-Wei and Chang, Ming-Ching and Chen, Ping-Yang and Byambaa Dorj and Hamad Al Jassmi and Ganzorig Batnasan and Fady Alnajjar and Mohammed Abduljabbar and Lin, Fang-Pang}, title = {FishEye8K: A Benchmark and Dataset for Fisheye Camera Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2023} }

此資料沒有可用的檢視。

其他資訊

欄位
最後更新資料 未知的
最後更新的詮釋資料 六月 2, 2023
建立 六月 2, 2023
格式 ZIP
共享範圍/授權 Creative Commons Attribution-NonCommercial 4.0
Media typeapplication/zip
formatZIP
id9461c310-d2b2-45b6-afa7-0e2b2169f74c
md5c93f2c08dc057c04e2fda60abb1ca31d
package id003a91f5-ac12-47e6-8309-be46a8a55f7c
position2
revision id6542dc14-5b32-4183-99f6-4b6161a31715
sha2565c4fc794e3829d872d85a64809938eb2e521c0166707274e952d99194c55463e
stateactive
建立超過 2 年之前

推薦資料集:


  • 空氣品質小時值_桃園市_平鎮站

    付費方式 免費
    更新頻率 不定期
    桃園市-平鎮站小時值
  • 第七號信號系統國內信號點碼核配現況

    付費方式 免費
    更新頻率 不定期
    第七號信號系統國內信號點碼核配現況
  • 遠距接見及訊問排程應用系統-重要應用系統簡介

    付費方式 免費
    更新頻率 不定期
    遠距接見及訊問排程應用系統-重要應用系統簡介
  • 契稅稅源統計月報表-10205

    付費方式 免費
    更新頻率 不定期
    提供本市各行政區102年1月起每月之契稅稅源統計資料-10205
  • 商業登記(依營業項目別)-公寓大廈管理服務業

    付費方式 免費
    更新頻率 不定期
    提供全國公寓大廈管理服務業(I801011)商業登記資料。