Source Code

MMC LAB

 

MoCA Source Code


  1. Windows source code for


  1. Shot Detection

  2. Rainer Lienhart. Comparison of Automatic Shot Boundary Detection Algorithms. In Image and Video Processing VII 1999, Proc. SPIE 3656-29, Jan. 1999. [PDF]


  3. Video OCR (text detection and text tracking)

  4. Rainer Lienhart and Wolfgang Effelsberg. Automatic Text Segmentation and Text Recognition for Video Indexing. ACM/Springer Multimedia Systems, Vol. 8. pp.69-81, January 2000.

  5. Also Technical Report TR-98-009, Praktische Informatik IV, University of Mannheim, May 1998. [PDF]


  6. Face Detection

  7. Rainer Lienhart, Silvia Pfeiffer, and Wolfgang Effelsberg. Video Abstracting. Communications of the ACM, Vol. 40, No. 12, pp.55-62, December 1997. [PDF] [PDF from ACM]


  8. In order to compile you need MS Visual C++ 6.0 and Microsofts DirectX 8.0 SDK. In MoCA_Lib/src/image/ you find the complete MoCA Library source code. In MoCA_Lib/src/prgs/ you find the source code for the different programs described here. The code is only available for non-commercial purposes.



Open Source Code


  1. Cross platform face detection code based on a cascade of boosted classifiers (part of OpenCV; directories apps/HaarFaceDetect and apps/HaarTraining)


  2. Rainer Lienhart and Jochen Maydt. An Extended Set of Haar-like Features for Rapid Object Detection. IEEE ICIP 2002, Vol. 1, pp. 900-903, Sep. 2002. [PDF]

  3. Rainer Lienhart, Alexander Kuranov, and Vadim Pisarevsky. Empirical Analysis of Detection Cascades of Boosted Classifiers for Rapid Object Detection. MRL Technical Report, Intel Labs, May 2002, revised Dec. 2002. [PDF]

  4. Rainer Lienhart, Luhong Liang, and Alexander Kuranov. A Detector Tree of Boosted Classifiers for Real-time Object Detection and Tracking. IEEE ICME2003, July 2003. [ICME2003.pdf]



2005 DARPA Grand Challenge Source Code


The 2005 DARPA Grand Challenge is a 132 mile race through the desert with autonomous robotic vehicles. Lasers mounted on the car roof provide a map of the road up to 20 meters ahead of the car but the car needs to see further in order to go fast enough to win the race. Computer vision can extend that map of the road ahead but desert road is notoriously similar to the surrounding desert. Various machine learning algorithm (Classification and Regression Trees) provided a machine learning boost to find road while at the same time measuring when that road could not be distinguished from surrounding desert.


Source code, videos, and ground truth data of

  1. Bob Davies and Rainer Lienhart. Using CART to Segment Road Images. SPIE Multimedia Content Analysis, Management, and Retrieval 2006, 15-19 Jan. 2006, San Jose, 2006. [PDF]

can be downloaded from here:

  1. Source code

  2. Ground truth data and videos