To promote research on flash photography for portrait matting, this work construct the first flash/no-flash portrait matting dataset. It consists of more than 100 diverse videos captured using the green screen, in total con-taining 3,025 well-annotated alpha mattes, named Flash-No-Flash Matting Dataset.
This dataset comprises images of parts from real industrial scenarios and virtual reality environments. Real images are sourced from actual industrial settings, ensuring both authenticity and diversity, while virtual reality images, which make up approximately 11% of the dataset, are captured through precise 3D modeling. Approximately 30% of the part information was manually authored by industry experts, while the remaining 70% was generated by multimodal large models such as Wenxin Yiyan and GPT-4.
The increasing number of wildfires damages nature and human life, making the early detection of wildfires in complex outdoor environments critical. With the advancement of drones and remote sensing technology, infrared cameras have become essential for wildfire detection. However, as the demand for higher accuracy in detection algorithms grows, the detection model's size and computational costs increase, making it challenging to deploy high-precision detection algorithms on edge computing devices onboard drones for real-time fire detection.
Existing RGB-T tracking research in general suffers from the challenge of a shortage of training data.
We collected fundus photos from the Kangnam Sacred Heart Hospital, Hallym University School of Medicine, Seoul, South Korea (IRB approval number: 2022-10-026), that were obtained from 2000 to September 2022. The fundus photographs were taken by five skilled examiners using the KOWA Nonmyd 8S Fundus Camera (KOWA company, Japan). Among the 2,000 images, we chose 50 test images that were characterized as ``bad-quality'' due to one of the following reasons: media opacity, small pupil, or poor patient cooperation.
This dataset consists of 462 field of views of Giemsa(dye)-stained and field(dye)-stained thin blood smear images acquired using an iPhone 10 mobile phone with a 12MP camera. The phone was attached to an Olympus microscope with 1000× objective lens. Half of the acquired images are red blood cells with a normal morphology and the other half have a Rouleaux formation morphology.
Nasal cytology is a medicine field that focuses on the examination of nasal mucosa cells with the objective of recognizing changes in the epithelium, which is frequently subjected to acute or chronic irritation and inflammation caused by viruses, bacteria, or fungi; in the last decade, nasal cytology is becoming increasingly critical in diagnosing nasal conditions.
Recognizing and categorizing banknotes is a crucial task, especially for individuals with visual impairments. It plays a vital role in assisting them with everyday financial transactions, such as making purchases or accessing their workplaces or educational institutions. The primary objectives for creating this dataset were as follows:
This data package（.zip） includes data of follower robots' motion track、errors and velocities in five simulatd experimental cases：(1),(2): set obstacle range on 0.8m and 1.0m，2 groups；(3): oneside situation, and the number of follower robots rises to 5. (4)：complex environment, which we place more obstacles. （5): change the lead-follower formation （6),(7)：two types of formation tracks, circle and straight line，compare follower1，2.
