Fisheye8K_all_including_train&test_1.zip

URL: https://scidm.nchc.org.tw/ja/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} }

このリソースのために作成されたビューはまだありません

追加情報

フィールド
最終更新日 unknown
メタデータ最終更新日時 2023 / 6月 / 2,
作成日 2023 / 6月 / 2,
データ形式 ZIP
ライセンス 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
作成日2 年以上前

推薦資料集:


  • 電器商品標示基準

    Payment instrument Free
    Update frequency Irregular
    電器商品標示基準
  • 取得臺南市核發之廢食用油回收車輛工作證者清冊

    Payment instrument Free
    Update frequency Irregular
    本資料集提供取得臺南市核發之廢食用油回收車輛工作證者清冊資訊
  • 僑界急難救助協會

    Payment instrument Free
    Update frequency Irregular
    旅居海外僑民發揮僑界血濃於水的關懷及善意,建立一個全球性的僑界急難救助網絡,協助駐外館處推動旅外國人急難救助工作。本資料集內容包括全球各地區僑界急難救助協會之所在地、團體名稱、團體聯絡資訊。
  • 重要國家醫療與網路發展指標

    Payment instrument Free
    Update frequency Irregular
    為了解重要國家醫療與網路發展情形,蒐集世界衛生組織之智慧醫療各國調查資料,以作為業務推動參考。
  • 歷年土壤調查_環保署土壤重金屬含量調查(1600公頃)

    Payment instrument Free
    Update frequency Irregular
    民國71至75年,環保署針對全國116萬餘公頃農田的土壤,以1,600公頃為單位網格,進行大樣區土壤的概況調查,並依調查結果參考專家學者共同訂定的「臺灣地區土壤重金屬含量及等級區分表」作為分級標準,調查結果重金屬含量偏高,即分級標準達四級或五級以上地區約30萬餘公頃,本次調查為臺灣地區土壤重金屬污染情況提供一個概略的描繪。土壤重金屬檢測分析方法,鎘、鉻...