Machine learning
A partnership between Protein Industries Canada and three companies, Grain Discovery, Inarix, and Sevita International, aims to bring artificial intelligence into the grain industry, enhancing Canada's trusted grain quality system. The companies will develop a smartphone-based grain quality assurance tool that leverages AI to provide real-time quality assessments,
Machine learning
As the field of robotics and autonomous driving continues to advance, researchers are developing new computer vision and machine learning algorithms that incorporate three-dimensional data. However, debugging these 3D models often requires a deeper understanding of their behavior within a spatio-temporal context, necessitating new visualization tools. A team of researchers
Machine learning
A new method for recognizing small targets in computer vision has been proposed by researchers from the School of Electrical and Information Engineering, Zhuhai Coll Sci & Technol. The method, based on an improved version of You Only Look Once Version 8 (YOLOv8), addresses the challenge of reduced detection accuracy
Machine learning
Researchers at a leading institution have made a breakthrough in understanding the genetic basis of growth-related traits in snapper (Chrysophrys auratus), a species commonly farmed for food. The study, published on biorxiv.org, involves the analysis of phenotypic and genomic data from a selectively bred population of snapper. The researchers
Machine learning
A partnership between Protein Industries Canada and three companies, Grain Discovery, Inarix, and Sevita International, aims to bring artificial intelligence into the grain industry, enhancing Canada's trusted grain quality system. The companies will develop a smartphone-based grain quality assurance tool that leverages AI to provide real-time quality assessments,
Machine learning
Researchers at the Hanoi University of Science and Technology have made significant strides in the field of artificial intelligence, specifically in the area of person re-identification (Re-ID). This critical computer vision task involves matching images of a person across multiple non-overlapping cameras. The study focuses on addressing the challenge of
Machine learning
Researchers from Shenyang Jianzhu University have published a study on Mathematics, detailing a novel point cloud classification method based on feature selection and ensemble learning. With the aid of the Liaoning Provincial Department of Science and Technology and People's Livelihood Science and Technology Plan Project, the team developed
Machine learning
New research from Jadavpur University introduces a machine learning-based approach to one-shot meta-learning for more efficient object tracking. The proposed hybrid model refines predictions from traditional tracking methods using machine learning to enhance performance, achieving a frame rate of 13.74 FPS while maintaining a trade-off between accuracy and computational
Machine learning
Research from Guangxi University has proposed a novel architecture called the Scale Transformer Small Object Detection Network (STSODNet) to address the challenges in detecting small objects in complex scenes. The STSODNet architecture presents a multiscale feature enhancement module to mitigate the effect of scale variations, and a refined spatial attention
Artificial intelligence
The AI in Computer Vision Market is poised to experience significant growth over the next decade, driven by the increasing adoption of AI-powered vision systems in key industries such as healthcare, automotive, and retail. The market, which was valued at USD 24.26 billion in 2023, is expected to reach
Artificial intelligence
BrainChip Holdings Ltd, the world's first commercial producer of ultra-low power, fully digital, event-based neuromorphic AI, will participate in the Embedded Vision Summit, taking place May 20-22, 2025, in Santa Clara, CA. Dr. M. Anthony Lewis, the company's Chief Technology Officer, will present a session on
Artificial intelligence
Researchers at Al-Nahrain University have developed an improved edge detection algorithm by integrating machine learning into the traditional Canny algorithm. The new approach involves replacing the Gaussian filter with a bilateral filter and estimating Canny algorithm thresholds using the Flower Pollination algorithm. The enhanced algorithm was evaluated using 50 images
