A Real-Time Evolutionary Object Recognition System

Evolvable Systems: From Biology to Hardware

2010

Self Cite

Abstract. Using GPU processing, it is now possible to develop an evolutionary vision system working at interactive frame rates. Our system uses motion as an important cue to evolve detectors which are able to detect an object when this cue is not available. Object detectors consist of a series of high level operators which are applied to the input image. A matrix of low level point operators are used to recombine the output of the high level operators. With this contribution, we investigate, which image processing operators are most useful for object detection. It was found that the set of image processing operators could be considerably reduced without reducing recognition performance. Reducing the set of operators lead to an increase in speedup compared to a standard CPU implementation. MotivationIn the field of evolutionary computer vision, evolutionary algorithms are used to search for optimal or approximately optimal solutions for computer vision problems [2]. A programmer developing a computer vision algorithm needs to decide in what sequence well known image processing operators have to be arranged to obtain a desired result. In evolutionary computer vision, Genetic Programming [1,13] is used to arrange different image processing operators to obtain a particular output or to perform a given task such as object recognition. This approach is particularly interesting for problems for which the solution is not readily apparent to those skilled in the art. Unfortunately, most experiments in evolutionary computer vision require enormous computational resources because multiple algorithms have to be evaluated over several generations to find an appropriate solution. However, the graphics processing unit (GPU) of a PC can be used for speeding up image processing tasks [7,8]. The GPU is ideal for speeding up image processing as the same operation usually needs to be computed for each image pixel.We have created a GPU accelerated evolutionary image processing system which is able to learn how to detect a user-specified object in an image [3,4].

“…The set of image processing operators is shown in Figure 4. The operators have been fully described in [4].…”

Section: Methodsmentioning

confidence: 99%

“…We have created a GPU accelerated evolutionary image processing system which is able to learn how to detect a user-specified object in an image [3,4].…”

Section: Motivationmentioning

confidence: 99%

“…The complete list of operators is given by Ebner [4]. The representation of the individuals will be described below.…”

Section: Motivationmentioning

confidence: 99%

Section: Representationmentioning

confidence: 99%

mentioning

confidence: 99%

See 3 more Smart Citations

Evolving Object Detectors with a GPU Accelerated Vision System

Evolvable Systems: From Biology to Hardware

2010

Self Cite

Engineering of Computer Vision Algorithms Using Evolutionary Algorithms

Advanced Concepts for Intelligent Vision Systems

2009

Self Cite

Abstract. Computer vision algorithms are currently developed by looking up the available operators from the literature and then arranging those operators such that the desired task is performed. This is often a tedious process which also involves testing the algorithm with different lighting conditions or at different sites. We have developed a system for the automatic generation of computer vision algorithms at interactive frame rates using GPU accelerated image processing. The user simply tells the system which object should be detected in an image sequence. Simulated evolution, in particular Genetic Programming, is used to automatically generate and test alternative computer vision algorithms. Only the best algorithms survive and eventually provide a solution to the user's image processing task.

Towards Automated Learning of Object Detectors

Applications of Evolutionary Computation

2010

Self Cite

Abstract. Recognizing arbitrary objects in images or video sequences is a difficult task for a computer vision system. We work towards automated learning of object detectors from video sequences (without user interaction). Our system uses object motion as an important cue to detect independently moving objects in the input sequence. The largest object is always taken as the teaching input, i.e. the object to be extracted. We use Cartesian Genetic Programming to evolve image processing routines which deliver the maximum output at the same position where the detected object is located. The graphics processor (GPU) is used to speed up the image processing. Our system is a step towards automated learning of object detectors.