Resources
Abnormal Human Action (AbHA) Dataset
The Abnormal Human Action dataset (AbHA) Abnormal Human Action Dataset (AbHA) includes five commonly occurring abnormal actions in day-to-day lives of the elderly people: ‘chest pain’, ‘headache’, ‘fainting’ and ‘falling backward’ and ‘falling forward’. Each action is performed by eight different individuals and repeated two times. Hence, total generated samples are 80 (8×2×5). The dataset is captured by Microsoft’s Kinect depth sensor v1. The resolution of depth videos is 640X480. 20 skeleton joints are captured in 3D coordinate system ('action_1mainWorld.txt') and depth coordinate system (‘action_1mainM.txt’) for each frame.
Reference:
Chhavi Dhiman, D. K. Vishwakarma, "A Robust Framework for Abnormal Human Action Recognition using R-Transform and Zernike Moments in Depth Videos", IEEE Sensors Journal, Vol. 19, No. 13, pp. 5195 - 5203, 2019.Impact Factor: 3.073
Multi Crop Vegetable Fruits (Multi CVF) dataset
A novel “Multi Crop Vegetable Fruits” (Multi CVF) dataset is collected that contains a total of 7500 images from 15 distinct classes representing crops vegetables and fruits. Each category contains 500 images. It contains two subsets- manually collected fruit, vegetable and crop samples as subset 1 and automatically collected fruit, vegetable and crop samples subset 2. Subset 2 provides more challenging samples collected randomly originally captured at different scales from google search.
15 classes covered in both subset 1 and subset 2 are as follows:
Apricot Fruit
Banana
Cauliflower
Corn
Golden Apple fruit
Guava Fruit
Kiwi Fruit
Lychee fruit
Peach Fruit
Pine apple fruit
Red Onion
12. Rice crop
13. Sugarcane
14. Walnut
15. Wheat
It is divided in train, val, test samples for both subsets.
Reference:
Sachin Kumar, Chhavi Dhiman, "Transfer Learning Based Automated Crop Analysis", IEEE International Conference on “Machine Learning, Big Data, Cloud and Parallel Computing: Trends, Perspectives and Prospects (Com-IT-Con-2022), Fardabad, India, 26-27th, May, 2022.