Illumination Invariant Color Model for Object Recognition in Robot Soccer

Luan, Xin; Qi, Weiwei; Song, Dalei; Ming, Chen; Zhu, Tieyi; Wang, Li

doi:10.1007/978-3-642-13498-2_89

Cited by 10 publications

(6 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Variations due to differences in distance/scale, orientation and illumination are addressed in literatures either individually [11], [12], [13], or together [14]. While algorithms relying on machine learning and similarity measurements may produce reasonable results, we believe that an explicit model of effect of such variations on each feature can guarantee performance and avoid unsupervised machine learning drifts and artifacts.…”

Section: Problem Statement and Related Workmentioning

confidence: 97%

An adaptive evidence structure for Bayesian recognition of 3D objects

Naguib

Lee

2015

Proceedings of the 9th International Conference on Ubiquitous Information Management and Communication

View full text Add to dashboard Cite

Classification of an object under various environmental conditions is a challenge for developing a reliable service robot. In this work, we show problems of using simple Naïve Bayesian classifier and propose a Tree-Augmented Naïve (TAN) Bayesian Networkbased classifier. We separate feature space into binary TRUE/FALSE regions which allows us to drive Bayesian inference prior conditional probabilities from statistical database. We go further using TRUE/FALSE regions to estimate expected posterior probabilities of each object under online specific conditions. These expectations are then used to select optimal feature sets under this environment and autonomously reconstruct Bayesian Network. Experimental results, validation and comparison show the performance of the proposed system.

show abstract

Section: Problem Statement and Related Workmentioning

confidence: 97%

An adaptive evidence structure for Bayesian recognition of 3D objects

Naguib

Lee

2015

Proceedings of the 9th International Conference on Ubiquitous Information Management and Communication

View full text Add to dashboard Cite

show abstract

“…The concept of a hybrid colour model, a colour model formed by combining channels from several existing models, is not unknown in the broader field of computer vision. For example, papers [LQS*10] and [JL04] document successful use of a model named HSY in robotic football. However, we were unable to find any paper mentioning use of such hybrid colour models in image retrieval.…”

Section: Previous Workmentioning

confidence: 99%

Improving Performance of Image Retrieval Based on Fuzzy Colour Histograms by Using Hybrid Colour Model and Genetic Algorithm

Ljubovic

Supic

2015

Computer Graphics Forum

View full text Add to dashboard Cite

A hybrid colour model is a colour descriptor formed by combining channels from several different colour models. Although rarely used in computer graphics applications due to redundancy, hybrid colour models may be of interest for the Content‐Based Image Retrieval (CBIR). Best features of each colour model can be combined to obtain optimal retrieval performance. This paper evaluates several approaches to the construction of a hybrid colour model that is used to construct a fuzzy colour histogram of image as a compact feature for retrieval. By evaluating each channel separately, a colour model named HSY is proposed. Various parameters of fuzzy histogram are further improved using Genetic algorithm (GA). Using standard data sets and the Average Normalized Modified Retrieval Rank (ANMRR) as a metric for retrieval performance, it is shown that this novel approach can give an improved retrieval performance.

show abstract

“…These color models are proposed in paper [12,13] based on robot soccer competition. These color models are invariant to illumination intensity, and they are constructed based on genetic algorithm (GA) and particle swarm optimization (PSO), having a large discriminating power for the object detection.…”

Section: E Color Modesl Hsy/rsc2/usbmentioning

confidence: 99%

“…Based on dichromatic reflection color model [10], Gevers and Smeulders [11] provided several color models invariant to significant changes in viewpoint, object geometry and illumination. In paper [12,13], several illumination invariant color models are proposed and successfully applied to semi-automation robot soccer game. In this paper, we apply the illumination invariant color models to underwater primary colors object recognition and evaluate their recognition performance.…”

Section: Introductionmentioning

confidence: 99%

Color model selection for underwater object recognition

Song

Sun

et al. 2014

2014 International Conference on Information Science, Electronics and Electrical Engineering

Self Cite

View full text Add to dashboard Cite

In this paper, the characteristics of underwater image and the importance of color features in underwater object recognition are presented. Classical illumination invariant color models are analyzed. Our goal is to study and evaluate the various color models in underwater object recognition applications. The illumination invariant color models yuv, c1c2c3, HSy, rSc2 and uSb are applied to carry out comparison experimental tests and the traditional primary colors of underwater targets are selected as object identification. The experiment object images with different illumination intensities are captured by a color video camera equipped in the underwater robotics. The comparison experimental results demonstrate that the yuv and uSb color model achieve high ART (Average Recognition Rate) and lower ERT (Error Recognition Rate).

show abstract

Illumination Invariant Color Model for Object Recognition in Robot Soccer

Cited by 10 publications

References 11 publications

An adaptive evidence structure for Bayesian recognition of 3D objects

An adaptive evidence structure for Bayesian recognition of 3D objects

Improving Performance of Image Retrieval Based on Fuzzy Colour Histograms by Using Hybrid Colour Model and Genetic Algorithm

Color model selection for underwater object recognition

Contact Info

Product

Resources

About