• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.4
• /
• pp.1989-2011
• /
• 2019

Vehicle detection based on aerial images is an interesting and challenging research topic. Most of the traditional vehicle detection methods are based on the sliding window search algorithm, but these methods are not sufficient for the extraction of object features, and accompanied with heavy computational costs. Recent studies have shown that convolutional neural network algorithm has made a significant progress in computer vision, especially Faster R-CNN. However, this algorithm mainly detects objects in natural scenes, it is not suitable for detecting small object in aerial view. In this paper, an accurate and effective vehicle detection algorithm based on Faster R-CNN is proposed. Our method fuse a hyperactive feature map network with Eltwise model and Concat model, which is more conducive to the extraction of small object features. Moreover, setting suitable anchor boxes based on the size of the object is used in our model, which also effectively improves the performance of the detection. We evaluate the detection performance of our method on the Munich dataset and our collected dataset, with improvements in accuracy and effectivity compared with other methods. Our model achieves 82.2% in recall rate and 90.2% accuracy rate on Munich dataset, which has increased by 2.5 and 1.3 percentage points respectively over the state-of-the-art methods.

• Journal of Korea Multimedia Society
• /
• v.13 no.5
• /
• pp.663-673
• /
• 2010

As a tool used for video maintenance, Video segmentation divides videos in hierarchical and structural manner. This technique can be considered as a core technique that can be applied commonly for various applications such as indexing, abstraction or retrieval. Conventional video segmentation used adaptive threshold to split video by calculating difference between consecutive frames and threshold value in window with fixed size. In this case, if the time difference between occurrences of cuts is less than the size of a window or there is much difference in neighbor feature, accurate detection is impossible. In this paper, Improved Adaptive threshold algorithm which enables determination of window size according to video format and reacts sensitively on change in neighbor feature is proposed to solve the problems above. Post-Processing method for decrement in error caused by camera flash and fast movement of large objects is applied. Evaluation result showed that there is 3.7% improvement in performance of detection compared to conventional method. In case of application of this method on modified video, the result showed 95.5% of reproducibility. Therefore, the proposed method is more accurated compared to conventional method and having reproducibility even in case of various modification of videos, it is applicable in various area as a video maintenance tool.

• Journal of KIISE:Software and Applications
• /
• v.32 no.11
• /
• pp.1121-1135
• /
• 2005

This paper proposes a moving object extraction method using the contrast map and salient points. In order to make the contrast map, we generate three-feature maps such as luminance map, color map and directional map and extract salient points from an image. By using these features, we can decide the Attention Window(AW) location easily The purpose of the AW is to remove the useless regions in the image such as background as well as to reduce the amount of image processing. To create the exact location and flexible size of the AW, we use motion feature instead of pre-assumptions or heuristic parameters. After determining of the AW, we find the difference of edge to inner area from the AW. Then, we can extract horizontal candidate region and vortical candidate region. After finding both horizontal and vertical candidates, intersection regions through logical AND operation are further processed by morphological operations. The proposed algorithm has been applied to many video sequences which have static background like surveillance type of video sequences. The moving object was quite well segmented with accurate boundaries.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.34 no.4
• /
• pp.333-339
• /
• 2010

Identification of a steady state is the first step in developing a fault detection and diagnosis (FDD) system of a heat pump. In a complete FDD system, the steady-state detector will be included as a module in a self-learning algorithm, which enables the working system's reference model to "tune" itself to its particular installation. In this study, a steady-state detector of a residential air conditioner based on moving windows was designed. Seven representative measurements were selected as key features for steady-state detection. The optimized moving-window size and the feature thresholds were decided on the basis of a startup-transient test and no-fault steady-state test. Performance of the steady-state detector was verified during an indoor load-change test. In this study, a general methodology for designing a moving-window steady-state detector for applications involving vapor compression has been established.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.2B
• /
• pp.124-132
• /
• 2007

Where a wireless LAN and a cellular network coexist, a mobile node has to experience vertical handoffs to move between them. Immediately after the vertical handoffs, TCP must need adaptation latency to adjust its congestion window to the proper size at a newly arrived network to use full of a new end-to-end available bandwidth. Even though SACK TCP has the best performance among other regular TCPs in the previous studies, it still cannot use full of the new available bandwidth quickly due to its inefficient increasing way of congestion window. BIC TCP, that becomes a popular TCP in long fat networks, has great feature working well against vertical handoffs by increasing congestion window exponentially with TCP connection sustained. In this paper, we derive adaptation latency of SACK TCP and BIC TCP numerically, and verify them by simulations. We also find that the shorter adaptation latency of BIC TCP produces higher throughput than SACK TCP on vertical handoffs. Consequently, to get higher performance on vertical handoff situations, we propose to use BIC TCP.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.2059-2064
• /
• 2004

Texture analysis is an important role for automatic visual insfection. This paper presents an application of wavelet extension and Gray level co-occurrence matrix (GLCM) for detection of defect encountered in textured images. Texture characteristic in low quality images is not to easy task to perform caused by noise, low frequency and small dimension. In order to solve this problem, we have developed a procedure called wavelet image extension. Wavelet extension procedure is used to determine the frequency bands carrying the most information about the texture by decomposing images into multiple frequency bands and to form an image approximation with higher resolution. Thus, wavelet extension procedure offers the ability to robust feature extraction in images. Then the features are extracted from the co-occurrence matrices computed from the sub-bands which performed by partitioning the texture image into sub-window. In the detection part, Mahalanobis distance classifier is used to decide whether the test image is defective or non defective.

• Journal of Institute of Control, Robotics and Systems
• /
• v.13 no.11
• /
• pp.1074-1081
• /
• 2007

This paper presents a method for real-time face detection and tracking which combined Adaboost and Camshift algorithm. Adaboost algorithm is a method which selects an important feature called weak classifier among many possible image features by tuning weight of each feature from learning candidates. Even though excellent performance extracting the object, computing time of the algorithm is very high with window size of multi-scale to search image region. So direct application of the method is not easy for real-time tasks such as multi-task OS, robot, and mobile environment. But CAMshift method is an improvement of Mean-shift algorithm for the video streaming environment and track the interesting object at high speed based on hue value of the target region. The detection efficiency of the method is not good for environment of dynamic illumination. We propose a combined method of Adaboost and CAMshift to improve the computing speed with good face detection performance. The method was proved for real image sequences including single and more faces.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.7
• /
• pp.1487-1494
• /
• 2011

In this paper, a novel genre classification algorithm is proposed for music recommendation system. Especially, to improve the classification accuracy, the band-pass filter for octave-based spectral contrast (OSC) feature is designed considering the psycho-acoustic model and actual frequency range of musical instruments. The GTZAN database including 10 genres was used for 10-fold cross validation experiments. The proposed multiple-octave based OSC produces better accuracy by 2.26% compared with the conventional OSC. The combined feature vector based on the proposed OSC and mel-frequency cepstral coefficient (MFCC) gives even better accuracy.

• Journal of Korean Academy of Oral and Maxillofacial Radiology
• /
• v.18 no.1
• /
• pp.67-73
• /
• 1988

This study was performed to clarify the mechanism of clicking sound and locking on temporomandibular joint and to determine the radiographic findings of them by using computed tomogram. Through the preliminary study with cadavers, the proper scanning condition and the correlatonship between the anatomy of cadaver and computed tomogram had been determined. The subjects were consisted of 10 controls and 16 patients having clicking sound or locking on temporomandibular joint. By using Hitachi-W500 as computed tomographic device, direct axial views and sagittal views reformed according to the changes in window setting and using the non-linear fraction were taken and analyzed by visual method and measuring the attenuation numbers. The obtained results were as follows: 1. The density of the anterior band of meniscus showed isodense to the surrounding muscles in normal. 2. In patient group, affected side showed increased radiopaque area anterior to condyle and underneath articular eminence as the feature of anteriorly displaced meniscus on axial and sagittal views. 3. In patient group, the condyle was rotated postero-laterally in affected side. 4. Non-linear fraction highlightened the feature of anteriorly displaced meniscus.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.11
• /
• pp.95-101
• /
• 1999

In this paper, we propose an adaptive method of tracking multiple moving objects using contour and features in surrounding conditions. We use an adaptive background model for robust processing in surrounding conditions. Object segmentation model detects pixels thresholded from local difference image between background and current image and extracts connected regions. Data association problem is solved by using feature extraction and object recognition model in searching window. We use Kalman filters for real-time tracking. The results of simulation show that the proposed method is good for tracking multiple moving objects in highway image sequences.