Learn More
Just as optical flow is the two-dimensional motion of points in an image, scene flow is the three-dimensional motion of points in the world. The fundamental difficulty with optical flow is that only the normal flow can be computed directly from the image measurements, without some form of smoothing or regularization. In this paper, we begin by showing that(More)
Reality world model consists of real images and depth information computed from these images. Stereoscopic reconstructions provide a sense of complete immersion, and users can select their own viewpoints at view time, independent of the actual camera positions used to capture the event. T he different visual media we have today share two shortcomings:(More)
The DARPA PerceptOR program implements a rigorous evaluative test program which fosters the development of field relevant outdoor mobile robots. Autonomous ground vehicles are deployed on diverse test courses throughout the USA and quantitatively evaluated on such factors as autonomy level, waypoint acquisition, failure rate, speed, and communications(More)
Described is the development and testing of a robust vegetation detector for mobile robot navigation. A multispectral sensor was created out of a near-infrared and a visible light video camera. Vegetation was then detected by subtracting each pixel in the red channel of the visible-light image from the corresponding pixel in the near-infrared image and(More)
1. Abstract Current unmanned vehicle systems enable exploration of and travel through remote areas, but demand significant communications resources and constant human operation. DARPA and the US Army have recognized these limitations and are now pursuing semi-autonomous vehicle systems in the Future Combat Systems (FCS) program. FCS places high demands on(More)
Virtualized Reality creates a model of time-varying real-world events from image sequences. The model can be used for manipulating and combining these events, and for rendering new virtual images. In this paper, we present two recent enhancements to Virtualized Reality. We present Model Enhanced Stereo (MES) as a method to use widely separated images to(More)
The most challenging technical problems facing successful autonomous UGV operation in off-road environments are reliable sensing and perception. In this paper, we describe our progress over the last year toward solving these problems in Phase II of DARPA's PerceptOR program. We have developed a perception system that combines laser, camera, and(More)
The task of teleoperating a robot over a wireless video link is known to be very difficult. Teleoperation becomes even more difficult when the robot is surrounded by dense obstacles, or speed requirements are high, or video quality is poor, or wireless links are subject to latency. Due to high quality lidar data, and improvements in computing and video(More)