• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.11
• /
• pp.607-614
• /
• 2016

In this paper, we propose an intelligent fire learning and detection system using convolutional neural networks (CNN). Through the convolutional layer of the CNN, various features of flame and smoke images are automatically extracted, and these extracted features are learned to classify them into flame or smoke or no fire. In order to detect fire in the image, candidate fire regions are first extracted from the image and extracted candidate regions are passed through CNN. Experimental results on various image shows that our system has better performances over previous work.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.5
• /
• pp.2430-2436
• /
• 2013

This study suggests a method of detecting the still object, which becomes a cause of danger within the crossroad. The Inverse Perspective Transform was performed in order to make the object size consistent by being inputted the real-time image from CCTV that is installed within the crossroad. It established the detection area in the image with the perspective transform and generated the adaptative background image with the use of the moving information on object. The detection of the stop object was detected the candidate region of the stop object by using the background-image differential method. To grasp the appearance of truth on the detected candidate region, a method is proposed that uses the gradient information on image and EHD(Edge Histogram Descriptor). To examine performance of the suggested algorithm, it experimented by storing the images in the commuting time and the daytime through DVR, which is installed on the cross street. As a result of experiment, it could efficiently detect the stop vehicle within the detection region inside the crossroad. The processing speed is shown in 13~18 frame per second according to the area of the detection region, thereby being judged to likely have no problem about the real-time processing.

• Journal of Korea Multimedia Society
• /
• v.9 no.9
• /
• pp.1139-1149
• /
• 2006

This paper describes a novel and efficient algorithm, which extracts focused objects from still images with low depth-of-field (DOF). The algorithm unfolds into four modules. In the first module, a HOS map, in which the spatial distribution of the high-frequency components is represented, is obtained from an input low DOF image [1]. The second module finds OOI candidate by using characteristics of the HOS. Since it is possible to contain some holes in the region, the third module detects and fills them. In order to obtain an OOI, the last module gets rid of background pixels in the OOI candidate. The experimental results show that the proposed method is highly useful in various applications, such as image indexing for content-based retrieval from huge amounts of image database, image analysis for digital cameras, and video analysis for virtual reality, immersive video system, photo-realistic video scene generation and video indexing system.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.636-639
• /
• 2003

In this paper, we present a robust method for detecting other vehicles from n forward-looking CCD camera in a moving vehicle. This system uses edge and shape information to detect other vehicles. The algorithm consists of three steps: lane detection, ehicle candidate generation, and vehicle verification. First after detecting a lane from the template matching method, we divide the road into three parts: left lane, front lane, and right lane. Second, we set the region of interest (ROI) using the lane position information and extract a vehicle candidate from the ROI. Third, we use local orientation coding (LOC) edge image of the vehicle candidate as input to a pretrained neural network for vehicle recognition. Experimental results from highway scenes show the robustness and effectiveness of this method.

• Journal of Korea Multimedia Society
• /
• v.14 no.10
• /
• pp.1275-1286
• /
• 2011

This paper proposes a high speed systolic array architecture for full search block matching algorithm (FBMA). The pixels of the search area for a reference block are input only one time to find the matched candidate block and reused to compute the sum of absolute difference (SAD) for the adjacent candidate blocks. Each row of designed 2-dimensional systolic array compares the reference block with the adjacent blocks of the same row in search area. The lower rows of the designed array get the pixels from the upper row and compute the SAD with reusing the overlapped pixels of the candidate blocks within same column of the search area. This designed array has no data broadcasting and global paths. The comparison with existing architectures shows that this array is superior in terms of throughput through it requires a little more hardware.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.3
• /
• pp.1377-1389
• /
• 2016

This paper presents a target model update scheme for the mean-shift tracking with background weighted histogram. In the scheme, the target candidate histogram is corrected by considering the back-projection weight of each pixel in the kernel after the best target candidate in the current frame image is chosen. In each frame, the target model is updated by the weighted average of the current target model and the corrected target candidate. We compared our target model update scheme with the previous ones by applying several test sequences. The experimental results showed that the object tracking accuracy was greatly improved by using the proposed scheme.

• Journal of Institute of Control, Robotics and Systems
• /
• v.16 no.7
• /
• pp.625-631
• /
• 2010

This paper proposes lane recognition algorithm using lane prominence technique to extract lane candidate. The lane prominence technique is combined with embossing effect, lane thickness check, and lane extraction using mask. The proposed lane recognition algorithm consists of preprocessing, lane candidate extraction and lane recognition. First, preprocessing is executed, which includes gray image acquisition, inverse perspective transform and gaussian blur. Second, lane candidate is extracted by using lane prominence technique. Finally, lane is recognized by using hough transform and least square method. To evaluate the proposed lane recognition algorithm, this algorithm was applied to the detection of lanes in the rainy and night day. The experiment results showed that the proposed algorithm can recognize lane in various environment. It means that the algorithm can be applied to lane recognition to drive unmanned vehicles.

• IEIE Transactions on Smart Processing and Computing
• /
• v.2 no.4
• /
• pp.189-196
• /
• 2013

This paper presents a two-stage approach to detect pedestrians in video sequences taken from a moving vehicle. The first stage is a preprocessing step, in which potential pedestrians are hypothesized. During the preprocessing step, a difference image is constructed using a global motion estimation, vertical and horizontal edge maps are extracted, and the color difference between the road and pedestrians are determined to create candidate regions where pedestrians may be present. The candidate regions are refined further using the vertical edge symmetry features of the pedestrians' legs. In the next stage, each hypothesis is verified using the integral channel features and an AdaBoost classifier. In this stage, a decision is made as to whether or not each candidate region contains a pedestrian. The proposed algorithm was tested on a range of dataset images and showed good performance.

• Proceedings of the IEEK Conference
• /
• 2007.07a
• /
• pp.381-382
• /
• 2007

In this paper, crack detection technique of concrete bridge is proposed robust against shadow and noise. Our technique consists of two steps. In the first step, crack candidate region is detected by preprocessing. Preprocessing techniques such as median filter, isolated point filter and morphological techniques, use utilized for detection of crack candidate regions. In the final step, crack is detected from crack candidate region by considering any connectivity between cracks. By experimental results, performance is improved 6.8% over the existing method.

• Journal of the Institute of Convergence Signal Processing
• /
• v.9 no.1
• /
• pp.18-23
• /
• 2008

In this paper, we propose the input image selection-method to improve the reconstructed high-resolution (HR) image quality. To obtain ideal super-resolution (SR) reconstruction image, all input images are well-registered. However, the registration is not ideal in practice. Due to this reason, the selection of input images with low registration error (RE) is more important than the number of input images in order to obtain good quality of a HR image. The suitability of a candidate input image can be determined by using statistical and restricted registration properties. Therefore, we propose the proper candidate input Low Resolution(LR) image selection-method as a pre-processing for the SR reconstruction in automatic manner. In video sequences, all input images in specified region are allowed to use SR reconstruction as low-resolution input image and/or the reference image. The candidacy of an input LR image is decided by the threshold value and this threshold is calculated by using the maximum motion compensation error (MMCE) of the reference image. If the motion compensation error (MCE) of LR input image is in the range of 0 < MCE < MMCE then this LR input image is selected for SR reconstruction, else then LR input image are neglected. The optimal reference LR (ORLR) image is decided by comparing the number of the selected LR input (SLRI) images with each reference LR input (RLRI) image. Finally, we generate a HR image by using optimal reference LR image and selected LR images and by using the Hardie's interpolation method. This proposed algorithm is expected to improve the quality of SR without any user intervention.