New defense software combines thermal imaging and smart perception to spot and track ground threats with fewer false alarms.

Researchers at Binghamton have studied how wars, such as in Ukraine, have led to better landmine detection and don't require internet connections.

Today's antipersonnel land mines are small and often have plastic casings that standard metal detectors cannot register.

Humans have been successfully trained to spot AI-generated faces in a study led by researchers at the Australian National ...

Real-time object detection is a critical capability in computer vision, enabling systems to identify and localize objects instantly in dynamic environments. Recent advances leverage optimized ...

object-detection-dataset/ ├── train/ │ ├── images/ # 800 training images │ │ ├── image_001.jpg │ │ ├── image_002.jpg ...

Self-driving cars can’t afford mistakes. Missing a traffic light or a pedestrian could mean disaster. But object detection in dynamic urban environments? That’s hard. I worked on optimizing object ...

Abstract: Open-vocabulary object detection (OVOD) aims to detect the objects beyond the set of classes observed during training. This work introduces a straightforward and efficient strategy that ...

🔥 December, 2024. UniDet3D is now accepted at AAAI 2025. 🔥 September, 2024. UniDet3D is state-of-the-art in 6 indoor benchmarks: Superpoints for ScanNet and MultiScan are provided as a part of the ...

Abstract: Deep learning-based object detection models rely heavily on large-scale and precise annotations for training. However, manually annotating bounding-box annotations for such data is both time ...

San Jose invited tech companies to mount cameras on a vehicle in what appears to be first-of-its-kind experiment For the last several months, a city at the heart of Silicon Valley has been training ...