Tech & Engineering
Updates every hour. Last Updated: 4-Apr-2026 03:16 ET (4-Apr-2026 07:16 GMT/UTC)
Churches in Islamic countries
Vienna University of TechnologyReports and Proceedings
Vehicle re-identification breakthrough: Pair-flexible pose synthesis unlocks robust multi-camera tracking
Beijing Institute of Technology Press Co., LtdVehicle re-identification (Re-ID) stands as a cornerstone technology in intelligent transportation systems, enabling the tracking of individual vehicles across non-overlapping surveillance cameras in urban environments. Despite substantial progress in deep learning approaches, real-world deployment faces persistent obstacles from diverse vehicle poses caused by varying camera angles, viewpoints, and driving directions. These pose variations scatter feature representations of the same vehicle in the embedding space, leading to reduced discriminative power and lower identification accuracy. Traditional methods relying on deep metric learning struggle to bridge these gaps, as pose differences create discrete clusters even for identical vehicles, complicating reliable matching in practical traffic scenarios.
A recent study introduces an innovative strategy to mitigate this challenge by projecting vehicle images from diverse poses into a unified target pose, generating synthetic images that serve as pose-invariant auxiliary information to strengthen Re-ID models. Recognizing the high costs and logistical difficulties of acquiring paired images of the same vehicle from different cameras, researchers developed VehicleGAN, the first pair-flexible pose-guided image synthesis framework tailored for vehicle Re-ID. This end-to-end Generative Adversarial Network accepts a source vehicle image and a target pose as inputs, synthesizing the vehicle in the desired pose without depending on detailed 3D geometric models. VehicleGAN operates effectively in both supervised settings, using paired data when available, and unsupervised scenarios through a novel AutoReconstruction mechanism. In this self-supervised approach, the model transfers an image to the target pose and back to the original, reconstructing the input to learn robust transformations without requiring expensive paired annotations. This flexibility addresses key limitations of prior 3D-based methods, which demand precise camera parameters often unavailable in real surveillance setups, and supervised 2D methods burdened by labor-intensive labeling.
- Journal
- Green Energy and Intelligent Transportation
Fau Innovation Pilot Award supports pioneering shark bycatch solution
Florida Atlantic UniversityBusiness Announcement
A new shark deterrent developed at FAU could transform commercial fishing by dramatically reducing unintended shark bycatch. Created by Stephen Kajiura, Ph.D., the patent-pending device uses a simple zinc and graphite combination to generate a weak electric field that repels sharks without affecting target fish. Field tests have shown up to a 69% reduction in shark bycatch, offering a practical, low-cost solution to a persistent ecological and economic challenge.
Study reports a phone-based tool to monitor tissue health by measuring the oxygen in cells
Dartmouth CollegePeer-Reviewed Publication
- Journal
- Biosensors and Bioelectronics
AI could help social entrepreneurs unlock new sources of finance
University of East LondonBook Announcement
A new research chapter suggests that artificial intelligence could help tackle one of the biggest challenges social entrepreneurs face: getting the funding they need to grow.
SWOT opens a new era for lake monitoring
Journal of Remote SensingPeer-Reviewed Publication
- Journal
- Journal of Remote Sensing