Computer Vision and Data Mining Research Projects Longin Jan Latecki Computer and Information Sciences Dept. Temple University [email protected].

Computer Vision and Data Mining Research Projects

Longin Jan LateckiComputer and Information Sciences

Dept.Temple [email protected]

Research Projects

• Object detection and recognition in images

• Improving ranking of search queries

• Motion and activity detection in videos

• Merging laser range maps of multiple robots

Object detection and recognition based on contour parts

• Often only parts of objects are visible in images• We can detect and recognize such objects in

edge images by performing contour grouping with shape similarity

Edge image Detected object

Algorithmic overview

• Probabilistic approaches are needed to address noisy sensor information in robot perception.

• We use Rao-Blackwellized particle filtering that has been successfully applied to solve the robot mapping problem (SLAM).

• We use medial axis (skeleton) as our shape representation.

Methodology

•Supported by DOE, NNSA, NA-22 •NSF, Computer Vision Program

Sample evolution of particles

Iteration 2 Iteration 10

Iteration 14 Iteration 18

Experimental results

Bottle model Swan model Bird model

Reference models

Applications:Analysis of aerial and satellite images,

in particular object and change detection

Supported by LANL, RADIUS: Rapid Automated Decomposition of Images for Ubiquitous Sensing, PI: Lakshman Prasad, LANL

detected structures of interest at three different scales (in maroon).

the original aerial image detected parts of contours

Videos are obtained from the Temple University Police video surveillance system.

Object and activity detection results

Motion and activity detection in videos

Methodology: We use PCA to learn local background textures, and detect motion by analysisof texture trajectories.Many Video Surveillance Applications, e.g.,:Detection of moving objects and detection of abandon objects, e.g., around power plants

Human detection in infrared images and videos

original

improved

original

improved

query

Improving ranking for similarity queries

Improving ranking in face profile retrieval Original retrieval

Improved retrievalquery

Methodology: We use semi-supervised manifold learning to learn new distancesin the manifold spanned by the training data set.Further applications:This methods makes it possible to improve ranking of any queriesfrom images through text to concepts.

Prior based on motion model

• Our motion model is based on structure registration process between local maps which results in multi-modal prior.

Prior in odometry based motion model

Prior in our structure registration based motion

model

Merging maps of multiple robots

Experimental resultsDataset: NIST Maze data set

Sample individual local maps

Merged global map