The purpose of image stitching is to generate a panoramic image with a large viewing angle from a series of images. Panoramic images can be applied to many practical scenes, such as military, simulation, augmented rea...
详细信息
Our previously proposed linear approach for reducing the global drift of a video-based frame-to-frame trajectory estimation method corrects it at selected points in time based on the alignment of one past and the curr...
详细信息
This research project explores a paradigm shift in perceptual enhancement by integrating a Unified recognition Framework and Vision-Language Pre-Training in three-dimensional image reconstruction. Through the synergy ...
详细信息
Due to the complex environment and special corrosion reasons, the metal parts such as insulation fasteners and fittings of transmission lines have significant differences in the location and shape of corrosion, making...
详细信息
A hybrid system of computational intelligence that is designed to solve imagerecognition tasks is proposed. This system is a stacking hybrid of an adaptive neuro-fuzzy system and neo-fuzzy neuron that provides improv...
详细信息
Few-shot learning (FSL) aims to learn new visual categories from a limited number of labeled examples. The use of mutual information is beneficial for improving the discrimination of feature embeddings, which makes me...
详细信息
Knee osteoarthritis is a chronic disease that is common in the middle-aged and elderly population, mainly caused by damage or degeneration of the knee joint cartilage. Therefore, research on knee joint cartilage has s...
详细信息
Federated Learning (FL) is a privacy-preserving algorithm that enables multiple clients to collaboratively train a global model without sharing their local data. This learning algorithm is particularly valuable in pri...
详细信息
In today's era of booming artificial intelligent (AI) applications, smart camera products are widely used in many different practical application environments such as observation, monitoring, recognition and ident...
详细信息
The mainstream human activity recognition (HAR) algorithms are developed based on RGB cameras, which are easily influenced by low-quality images (e.g., low illumination, motion blur). Meanwhile, the privacy protection...
详细信息
暂无评论