|
The following is a list of active or recent projects. Click on the "Read more..." links below the brief descriptions to learn more about the individual projects. There is also a list of previous projects.
|
|
|
Helping Landing Signal Officers
We recently started a new project aimed at improving the data collection of landings on aircraft carriers. Landing Signal Officers (LSO) talk the pilots through the technically challenging precision maneuvers that are required to safely land on the carrier platform. Conversations and performance are logged along with video taken from the platform camera. The NPS Vision Lab is contributing with general project expertise and video-related knowledge in particular. The platform camera video needs to be segmented, stored, and analyzed for aircraft tracking.
More information can be found on the LSO Project web page.
|
|
|
|
|
Parts-Based Object Detection
In this set of projects, we are building on our posture recognition work to improve the algorithms for more diverse objects, better recall and lower false positive rates, and invariance to typical image transformations such as rotation.
|
|
|
Read more...
|
|
|
Experiments at Camp Roberts
Members of the NPS Vision Lab (Justin, Rob, Sam, Adan and Mathias (not in picture)) were conducting experiments at Camp Roberts in August 2010. Working together with other NPS faculty members and students, we flew remote-controlled (unmanned) planes with video cameras and analyzed the captured images.
|
|
|
Read more...
|
|
|
Posture Recognition for Automated Evaluation of MOUT Training
Detecting and classifying marines and their postures is critical for automated training performance evaluation. The main objective for this project is to detect articulated objects in various configurations in still images, with an unconstrained, cluttered background that can not be modeled. Our approach usesa multi-class boosting procedure that favors discriminative features shared by multiple objects and views. Unlike traditional methods, this approach scales logarithmically with the number of classes. Click here to see a video.
|
|
|
Read more...
|
|
|
Improving Crew Threat Awareness through Augmented Vision
The focus of this research and prototype system development is to integrate spatially related data into a synthetic view of the outside environment for use by vehicle commanders, via a visually augmented indirect vision system. Street names, building information and intelligence data will be fused with the video from vehicle-mounted cameras. Terrain-associated knowledge hence persists in place in the environment, rather than being verbally relayed, stored in text documents or on paper maps, or being lost entirely. Crucial information - unobtrusively displayed at the right moment and place - allows a vehicle crew to better understand their operational environment, to be aware of threats that may be present, and ultimately to improve situational awareness and crew safety.
|
|
|
Read more...
|
|
|
HandVu: Vision-based Hand Gesture Recognition and User Interface
Read more about HandVu or even download the software at the current HandVu web page.
|
|
|
|
|
|
|
Research
