• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.11
• /
• pp.181-186
• /
• 2014

The paper proposes a new method of segmentation-based feature extraction to improve performance in pedestrian upper-body detection. General pedestrian detectors that use local features are often plagued by false positives due to the locality. Color information of multi parts of the upper body is utilized in figure-ground segmentation scheme to extract an salient, "global" shape feature capable of reducing the false positives. The performance of the multi-part color segmentation-based feature is evaluated by changing color spaces and the parameters of color histogram. The experimental result from an upper-body dataset shows that the proposed feature is effective in reducing the false positives of local feature-based detectors.

• Journal of Advanced Navigation Technology
• /
• v.16 no.2
• /
• pp.394-400
• /
• 2012

SURF is a robust local invariant feature descriptor and has been used in many applications such as object recognition. Even though this algorithm has similar matching accuracy compared to the SIFT, which is another popular feature extraction algorithm, it has advantage in matching time. However, these descriptors do not consider relative location information of extracted interesting points to guarantee rotation invariance. Also, since they use gray image of original color image, they do not use the color information of images, either. In this paper, we propose a method for improving matching performance of SURF descriptor using the color and relative location information of interest points. The location information is built from the angles between the line connecting the centers of interest points and the orientation line constructed for the center of each interest points. For the color information, color histogram is constructed for the region of each interest point. We show the performance of our scheme through experiments.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.4
• /
• pp.1807-1823
• /
• 2016

Local Binary Pattern (LBP) and its variants have powerful discriminative capabilities but most of them just consider each LBP code independently. In this paper, we propose sub oriented histograms of LBP for smoke detection and image classification. We first extract LBP codes from an image, compute the gradient of LBP codes, and then calculate sub oriented histograms to capture spatial relations of LBP codes. Since an LBP code is just a label without any numerical meaning, we use Hamming distance to estimate the gradient of LBP codes instead of Euclidean distance. We propose to use two coordinates systems to compute two orientations, which are quantized into discrete bins. For each pair of the two discrete orientations, we generate a sub LBP code map from the original LBP code map, and compute sub oriented histograms for all sub LBP code maps. Finally, all the sub oriented histograms are concatenated together to form a robust feature vector, which is input into SVM for training and classifying. Experiments show that our approach not only has better performance than existing methods in smoke detection, but also has good performance in texture classification.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.9
• /
• pp.67-76
• /
• 2010

This paper proposes a image-based water level measurement method, which adapt to the ruler's surface condition. When the surface of a ruler is deteriorated by mud, drifts, or strong light reflection, the proposed method judges the pollution of ruler by comparing distance between two levels: the first one is the end position of horizontal edge region which keeps the pattern of ruler's marking, and the second one is the position where the sharpest drop occurs in the histogram which is construct using image density based on the axis of image height. If the ruler is polluted, the water level is a position of local valley of the section having a maximum difference between the local peak and valley around the second level. If the ruler is not polluted, the water level is detected as the position having horizontal edges more than 30% of histogram's maximum value around the first level. The detected water level is converted to the actual water level by using the mapping table which is construct based on the making of ruler in the image. The proposed method is compared to the ultrasonic based method to evaluate its accuracy and efficiency on the real situation.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2012.05a
• /
• pp.149-150
• /
• 2012

This paper presents a shot boundary detection method based on the global decision tree that allows for extraction of boundaries of high variations occurring due to camera breaks from frame difference values. For a start, difference values between frames are calculated through local X2-histogram and normalization. Next, the distances between difference values are calculated through normalization.

• Proceedings of the Korea Society for Industrial Systems Conference
• /
• 2003.11a
• /
• pp.145-156
• /
• 2003

This paper for real time object tracking in this treatise detect histogram analysis that is accumulation value of binary conversion density and edge information and body that move by real time use of difference Image techniques and proposed method to object tracking. Firstly, we extract edge that can reduce quantity of data keeping information about form of input image in object detection. Object is extracted by performing difference image and binarization in edge image. Area of detected object is determined by threshold value that divide sum of horizontal accumulation value about binary conversion density by value that add horizontalityㆍverticality maximum accumulation value. Object is tracked by comparing similarity with object that is detected in previous frame and present frame. As experiment result, proposed algorithm could improve the object detection speed, and could track object by real time and could track local movement.

• Convergence Security Journal
• /
• v.2 no.1
• /
• pp.77-86
• /
• 2002

In this paper, we propose a segmentation algorithm that can reliably separate moving objects from noisy background in the image sequence received from a camera at the fixed position. Image segmentation is one of the most difficult process in image processing and an adoption in the change of environment must be considered for the increase in the accuracy of the image. The proposed algorithm consists of four process : generation of the difference image between the input image and the reference image, removes the background noise using the background nois modeling to a difference image histogram, then selects the candidate initial region using local maxima to the difference image, and gradually expanding the connected regions, region by region, using the shape information. The test results show that the proposed algorithm can detect moving objects like intruders very effectively in the noisy environment.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.4
• /
• pp.12-20
• /
• 2011

In this paper, we propose an efficient object detection and classification algorithm for video surveillance applications. Previous researches mainly concentrated either on object detection or classification using particular type of feature e.g., Scale Invariant Feature Transform (SIFT) or Speeded Up Robust Feature (SURF) etc. In this paper we propose an algorithm that mutually performs object detection and classification. We combinedly use heterogeneous types of features such as texture and color distribution from local patches to increase object detection and classification rates. We perform object detection using spatial clustering on interest points, and use Bag of Words model and Naive Bayes classifier respectively for image representation and classification. Experimental results show that our combined feature is better than the individual local descriptor in object classification rate.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.10
• /
• pp.2464-2478
• /
• 2013

Image stitching techniques produce an image with a wide field-of-view by aligning multiple images with a narrow field-of-view. While conventional algorithms successfully stitch images with a small parallax, structure misalignment may occur when input images contain a large parallax. This paper presents an image stitching algorithm that aligns images with a large parallax by regional linear warping. To this end, input images are first approximated as multiple planar surfaces, and different linear warping is applied to each planar surface. For approximating input images as multiple planar surfaces, the concept of dominant edges is introduced. Dominant edges are defined as conspicuous edges of lines in input images, and extracted dominant edges identify the boundaries of each planar surface. Dominant edge extraction is conducted by detecting distinct changes of local characteristics around strong edge pixels. Experimental results show that the proposed algorithm successfully stitches images with a large parallax without structure misalignment.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.11C
• /
• pp.1076-1082
• /
• 2005

Recently, there have been much efforts in the image segmentation using morphological approach. Among them, the watershed algorithm is one of powerful tools which can take advantages of both of the conventional edge-based segmentation and region-based segmentation. The concept of watershed is based on topographic analogy. But, its high sensitivity to noise yields a very large number of resulting segmented regions which leads to oversegmentation. So we suggest the restricted waterfall algorithm which reduce the oversegmentation by eliminate not only local minima but also local maxima. As a result, the restricted waterfall algorithm has a good segmented image than the other methods, and has a better binary image than the histogram thresholding method.