FishEye8K: A Benchmark and Dataset for Fisheye Camera Object Detection

FishEye8K

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.

copyright

The FishEye8K dataset described on this page is distributed under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 License, which implies that you must: * (1) attribute the work as specified by the original authors, * (2) may not use this work for commercial purposes (for commercial use, please contact us), and * (3) if you alter, transform, or build upon this work, you may distribute the resulting work only under the same license. The dataset is provided "as it is" and we are not responsible for any subsequence from using this dataset.

資料與資源

額外的資訊

欄位
作者 Chung-I Huang, Jun-Wei Hsieh
最後更新 2024年7月12日, 下午2點29分 (UTC+00:00)
建立 2022年4月6日, 早上6點52分 (UTC+00:00)
copyright The FishEye8K dataset described on this page is distributed under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 License, which implies that you must: * (1) attribute the work as specified by the original authors, * (2) may not use this work for commercial purposes (for commercial use, please contact us), and * (3) if you alter, transform, or build upon this work, you may distribute the resulting work only under the same license. The dataset is provided "as it is" and we are not responsible for any subsequence from using this dataset.
DOI 10.30193/scidm-ds-571593m

Citation

Chung-I Huang, Jun-Wei Hsieh . (2022-04-06). FishEye8K: A Benchmark and Dataset for Fisheye Camera Object Detection. 國網資料集平台.


推薦資料集:


  • (水里鄉集集鎮信義鄉)109年公告現值公告地價資料

    付費方式 免費
    更新頻率 不定期
    南投縣公告現值及公告地價(係為產製當時之資料,後續因土地分割、合併等致地價變動,可利用南投縣公告土地現值、公告地價查詢系統(http://link.nantou.gov.tw/land/Land.aspx)所提供公告土地現值及公告地價查詢功能,如有土地合併或分割時,該系統會同步更新土地分割或合併後之地價資料;公告現值於每年1月1日公告,公告地價每2年公...
  • 新北市路邊收費停車場收費路段資訊-中和區

    付費方式 免費
    更新頻率 不定期
    包含板橋、新莊、三重、永和、中和、新店、土城、海山、蘆洲、樹林、鶯歌、三峽、汐止、林口、淡水、八里等地區路邊收費停車場收費路段資訊-中和區
  • 新北市NewTaipei熱點-平溪區

    付費方式 免費
    更新頻率 不定期
    新北市政府無線網路(NewTaipei)熱點資訊。-平溪區
  • 經濟部國營事業委員會預算

    付費方式 免費
    更新頻率 不定期
    本資料集包含歲出計畫提要及分支計畫概況表、人事費用分析表、公務車輛明細表、各項費用彙計表、預算員額明細表。
  • 臺北市人口死亡數按年齡別

    付費方式 免費
    更新頻率 不定期
    臺北市人口死亡數按年齡別時間數列統計資料