Investigating automated bird detection from webcams using machine learning

We provide a dataset of images(.jpeg) with their corresponding annotations files(.xml) used to train a bird detection deep learning model. These images were collected from the live stream feeds of Cornell Lab of Ornithology (https://www.allaboutbirds.org/cams/) situated in 6 unique locations around the world as follows: Treman bird feeding garden at the Cornell Ornithology Laboratory in Ithaca, New York. At this station, Axis P11448-LE cameras are used to capture the recordings from feeders perched on the edge of both sapsucker woods and its 10-acre ponds. This site mainly attracts forest species like chickadees (Poecile atricapillus), red-winged blackbirds (Agelaius phoeniceus), and woodpeckers (Picidae). A total of 2065 images were captured from this location. Fort Davis in Western Texas, USA. At this site, a total of 30 hummingbird feeder cams are hosted at an elevation of over 5500 feet. From this site, 1440 images were captured. Sachatamia Lodge in Mindo, Ecuador. This site has a live hummingbird feed watcher that attracts over 132 species of hummingbirds including: Fawn-breasted Brilliant, White-necked Jacobin, Purple-bibbed Whitetip, Violet-tailed Sylph, Velvet-purple Coronet, and many others. A total of 2063 images were captured from this location. Morris County, New Jersey, USA. Feeders at this location attract over 39 species including Red-bellied Woodpecker, Red-winged Blackbird, Purple Finch, Blue Jay, Pine Siskin, Hairy Woodpecker, and others. Footage at this site is captured by an Axis P1448-LE Camera and Axis T8351 Microphone. A total of 1876 images were recorded from this site. Canopy Lodge in El Valle de Anton, Panama. Over 158 bird species visit this location annually and these include Gray-headed Chachalaca, Ruddy Ground-Dove, White-tipped Dove, Green Hermit, and others. A total of 1600 images were captured. Southeast tip of South Island, New Zealand. At this site, nearly 10000 seabirds visit this location annually and a total of 1548 images were captured. The Cornell Lab of Ornithology is an institute dedicated to biodiversity conversation with the main focus on birds through research, citizen science, and education. The autoscreen software was used to capture the images from the live feeds and images of approximately 1 Megapixel (Joint Photographic Experts Group) JPEG coloured images of resolution $1366\times 768 \times 3$ pixels were collected (https://sourceforge.net/projects/autoscreen/). The software was taking a new image every 30 seconds and were captured during different times of the day in order to avoid a sample biased dataset. In total, 10592 images were collected for this study. Files provided Train.zip – contains 6779 image files(.jpeg) and 6779 annotation files (.xml) Validation.zip – contains 1695 image files(.jpeg) and 1695 annotation files (.xml) Test.zip –contains 2118 image files(.jpeg) Scripts.zip - Contains scripts needed in manipulating the dataset like dataset partitioning, creation of CSV and tfrecords files. This dataset was used in the MSc thesis titled “Investigating automated bird detection from webcams using machine learning” by Alex Mirugwe, University of Cape Town – South Africa.

本数据集提供了用于训练鸟类检测深度学习模型的图像（.jpeg）及其对应标注文件（.xml）。这些图像采集自康奈尔鸟类学实验室（Cornell Lab of Ornithology）的全球6个不同点位的直播流，具体点位如下：
1. 纽约州伊萨卡市康奈尔鸟类学实验室特雷曼鸟类喂食园。该站点使用Axis P11448-LE型摄像头，采集安装在吸汁啄木鸟林及10英亩池塘边缘的喂食器录制画面。该站点主要吸引山雀（Poecile atricapillus）、红翅黑鹂（Agelaius phoeniceus）、啄木鸟（Picidae）等森林鸟类，共采集图像2065张。
2. 美国德克萨斯州西部戴维斯堡。该站点部署了30台蜂鸟喂食器摄像头，部署海拔超过5500英尺，共采集图像1440张。
3. 厄瓜多尔明多的萨查塔米亚旅馆。该站点设有活体蜂鸟喂食观测点，吸引包括棕胸辉蜂鸟、白颈雅各宾蜂鸟、紫领白尾蜂鸟、紫尾仙蜂鸟、天鹅绒紫冠蜂鸟等在内的132余种蜂鸟，共采集图像2063张。
4. 美国新泽西州莫里斯县。该站点的喂食器吸引包括红腹啄木鸟、红翅黑鹂、紫朱雀、冠蓝鸦、松金翅雀、多毛啄木鸟等在内的39余种鸟类，画面由Axis P1448-LE型摄像头与Axis T8351型麦克风采集，共记录图像1876张。
5. 巴拿马埃尔巴列德安东的冠层旅馆。该站点每年接待超过158种鸟类，包括灰头稚冠雉、红地鸠、白顶鸠、绿隐蜂鸟等，共采集图像1600张。
6. 新西兰南岛东南端。该站点每年有近10000只海鸟到访，共采集图像1548张。

康奈尔鸟类学实验室是一家致力于生物多样性保护的科研机构，核心聚焦鸟类研究，通过科研、公民科学与教育三大方向开展工作。本数据集使用autoscreen软件从直播流中采集图像，采集得到的图像为约1兆像素的彩色联合图像专家组（Joint Photographic Experts Group，JPEG）图像，分辨率为1366×768×3像素，相关软件开源地址为https://sourceforge.net/projects/autoscreen/。该软件每30秒捕获一张新图像，且在一天中的不同时段进行采集，以避免数据集样本出现偏差。本研究共采集图像10592张。

本次提供的数据集文件如下：
- 训练集压缩包（Train.zip）：包含6779张图像文件（.jpeg）与6779个标注文件（.xml）
- 验证集压缩包（Validation.zip）：包含1695张图像文件（.jpeg）与1695个标注文件（.xml）
- 测试集压缩包（Test.zip）：包含2118张图像文件（.jpeg）
- 脚本压缩包（Scripts.zip）：包含用于数据集处理的各类脚本，例如数据集划分、CSV与tfrecords文件生成脚本。

本数据集曾用于南非开普敦大学Alex Mirugwe的硕士学位论文《基于机器学习的网络摄像头鸟类自动检测研究》（英文原题："Investigating automated bird detection from webcams using machine learning"）。