Aaron F. Bobick

Learn More
ÐA new view-based approach to the representation and recognition of human movement is presented. The basis of the representation is a temporal templateÐa static vector-image where the vector value at each point is a function of the motion properties at the corresponding spatial location in an image sequence. Using aerobics exercises as a test domain, we(More)
In this paper we introduce a new algorithm for image and video texture synthesis. In our approach, patch regions from a sample image or video are transformed and copied to the output and then stitched together along optimal seams to generate a new (and typically larger) output. In contrast to other techniques, the size of the patch is not chosen(More)
We present a novel technique for texture synthesis using optimization. We define a Markov Random Field (MRF)-based similarity metric for measuring the quality of synthesized texture with respect to a given input sample. This allows us to formulate the synthesis problem as minimization of an energy function, which is optimized using an Expectation(More)
!"#$%&'$?@7'+ A-A"3 1"+#3'4"+ A3$4-4'.'+('# +5&(-#('# -AA3$-#7 ($ (7" 1"("#('$& -&1 3"#$%&'('$& $) ("BA$3-..5 "C("&1"1 -#('0'('"+ -&1 '&("3-#('$&+ 4"(D""& B,.('A." -%"&(+: @7" ),&1-B"&(-. '1"'+ ($ 1'0'1" (7" 3"#$%&'('$& A3$4."B '&($ (D$ ."0".+: @7" .$D"3 ."0". 1"("#('$&+ -3" A"3)$3B"1 ,+'&% +(-&1-31 '&1"A"&1"&( A3$4-4'.'+('# "0"&( 1"("#($3+ ($ A3$A$+"(More)
ÐA new method for the representation, recognition, and interpretation of parameterized gesture is presented. By parameterized gesture we mean gestures that exhibit a systematic spatial variation; one example is a point gesture where the relevant parameter is the two-dimensional direction. Our approach is to extend the standard hidden Markov model method of(More)
A new view-based approach to the representation and recognition of action is presented. The basis of the representation is a temporal template | a static vector-image where the vector value at each point is a function of the motion properties at the corresponding spatial location in an image sequence. Using 18 aerobics exercises as a test domain, we explore(More)
A method for solving the stereo matching problem in the presence of large occlusion is presented. A data structure—the disparity space image—is defined to facilitate the description of the effects of occlusion on the stereo matching process and in particular on dynamic programming (DP) solutions that find matches and occlusions simultaneously. We(More)
A probabilistic framework for representing and visually recognizing complex multi-agent action is presented. Motivated by work in model-based object recognition and designed for the recognition of action from visual evidence, the representation has three components: (1) temporal structure descriptions representing the temporal relationships between agent(More)
A new view-based approach to the representation and recognition of action is presented. The basis of the representation is a temporal template a static vector-image where the vector value at each point is a function of the motion properties at the corresponding spatial location in an image sequence. Using 18 aerobics exercises as a test domain, we explore(More)
This paper presents several approaches to the machine perception of motion and discusses the role and levels of knowledge in each. In particular, different techniques of motion understanding as focusing on one of movement, activity or action are described. Movements are the most atomic primitives, requiring no contextual or sequence knowledge to be(More)