Evolving a Task Specific Image Operator

Ebner, Marc; Zell, Andreas

doi:10.1007/10704703_6

Cited by 38 publications

(28 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first work in this area employed GP to evolve an operator for detecting interest points [4]. Trujillo and Olague [31] have also used GP to generate feature extractors for computer vision applications.…”

Section: Related Workmentioning

confidence: 99%

Genetic Programming-Evolved Spatio-Temporal Descriptor for Human Action Recognition

Liu¹,

Shao²,

Rockett³

2012

Procedings of the British Machine Vision Conference 2012

View full text Add to dashboard Cite

The potential value of human action recognition has led to it becoming one of the most active research subjects in computer vision. In this paper, we propose a novel method to automatically generate low-level spatio-temporal descriptors showing good performance, for high-level human-action recognition tasks. We address this as an optimization problem using genetic programming (GP), an evolutionary method, which produces the descriptor by combining a set of primitive 3D operators. As far as we are aware, this is the first report of using GP for evolving spatio-temporal descriptors for action recognition. In our evolutionary architecture, the average cross-validation classification error calculated using the support-vector machine (SVM) classifier is used as the GP fitness function. We run GP on a mixed dataset combining the KTH and the Weizmann datasets to obtain a promising feature-descriptor solution for action recognition. To demonstrate generalizability, the best descriptor generated so far by GP has also been tested on the IXMAS dataset leading to better accuracies compared with some previous hand-crafted descriptors.

show abstract

Section: Related Workmentioning

confidence: 99%

Genetic Programming-Evolved Spatio-Temporal Descriptor for Human Action Recognition

Liu¹,

Shao²,

Rockett³

2012

Procedings of the British Machine Vision Conference 2012

View full text Add to dashboard Cite

show abstract

“…Using evolutionary algorithms, it is possible to evolve adaptive operators which are optimal or near optimal for a given task [6]. Poli [18] has shown that Genetic Programming is particularly useful for image processing.…”

Section: Evolutionary Computer Visionmentioning

confidence: 99%

Evolving Object Detectors with a GPU Accelerated Vision System

Ebner

2010

Evolvable Systems: From Biology to Hardware

Self Cite

View full text Add to dashboard 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].

show abstract

“…However, early on, it was clear that in principle these techniques could be used to create fully adaptive operators which would be optimal or near optimal for the task at hand [7]. It was also clear that Genetic Programming would be particularly useful for image analysis [8].…”

Section: Evolutionary Computer Visionmentioning

confidence: 99%

A Real-Time Evolutionary Object Recognition System

Ebner

2009

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. We have created a real-time evolutionary object recognition system. Genetic Programming is used to automatically search the space of possible computer vision programs guided through user interaction. The user selects the object to be extracted with the mouse pointer and follows it over multiple frames of a video sequence. Several different alternative algorithms are evaluated in the background for each input image. Real-time performance is achieved through the use of the GPU for image processing operations.

show abstract

Evolving a Task Specific Image Operator

Cited by 38 publications

References 16 publications

Genetic Programming-Evolved Spatio-Temporal Descriptor for Human Action Recognition

Genetic Programming-Evolved Spatio-Temporal Descriptor for Human Action Recognition

Evolving Object Detectors with a GPU Accelerated Vision System

A Real-Time Evolutionary Object Recognition System

Contact Info

Product

Resources

About