
Scientists adopt deep learning for multi-object tracking
Research News Release
EurekAlert! provides eligible reporters with free access to embargoed and breaking news releases.
Eligibility GuidelinesEurekAlert! offers eligible public information officers paid access to a reliable news release distribution service.
Eligibility GuidelinesEurekAlert! is a service of the American Association for the Advancement of Science.
Implementing algorithms that can simultaneously track multiple objects is essential to unlock many applications, from autonomous driving to advanced public surveillance. However, it is difficult for computers to discriminate between detected objects based on their appearance. Now, researchers at the Gwangju Institute of Science and Technology (GIST) adapted deep learning techniques in a multi-object tracking framework, overcoming short-term occlusion and achieving remarkable performance without sacrificing computational speed.
Creating new procedures that improve mass drone traffic is the purpose of LABYRINTH, a European research project coordinated by the Universidad Carlos III de Madrid (UC3M) with the participation of 13 international organisations within the R&D&I, transport, emergency, and auxiliary services fields. Researchers hope to use these drone swarm applications to improve civil road, train, sea, and air transport, making it safer, more efficient, and more sustainable.
The July 2021 issue of IEEE/CAA Journal of Automatica Sinica features six articles that showcase the potential of machine learning in its various forms. The applications described in the studies range from advanced driver assistance systems and computer vision to image processing and collaborative robotics.
Researchers from the National Institute of Information and Communications Technology (NICT), Network Research Institute, succeeded the first S, C and L-bands transmission over long-haul distances in a 4-core optical fiber with standard outer diameter (0.125 mm). The researchers constructed a transmission system that makes full use of wavelength division multiplexing technology by combining different amplifier technologies, to achieve a transmission demonstration with date-rate of 319 terabits per second, over a distance of 3,001 km.
Older people affected by memory loss have much to gain from AR technology, yet a study from the University of Bath in the UK exploring the use of augmented reality to support older adults at home finds the user interface is sometimes confusing for those aged 50+.
New research shows that students rate the usefulness and usability of this virtual tool very positively
Researchers at Aalto University have harnessed the power of chatbots to help designers and developers develop new apps and allow end users to find information on the apps on their devices. The chatbot 'Hey GUI' can answer questions by showing images and screenshots of apps, or through simple text phrases.
A novel, two-step cryptography technique is the first to combine genetic technology with mathematical techniques to generate a complex cryptographic environment with high security and flexibility. In experiments, the proposed algorithm outperformed existing algorithms based on a variety of parameters.
Older people affected by memory loss have much to gain from AR technology, yet a study from the University of Bath in the UK, exploring the use of augmented reality to support older adults at home finds the user interface is sometimes confusing for those aged 50+.
A smartphone-based eye screening and referral system used in the community has been shown to almost triple the number of people with eye problems attending primary care, as well as increasing appropriate uptake of hospital services, compared to the standard approach. The new findings come from research carried out in Kenya, published in The Lancet Digital Health.