• Journal of Broadcast Engineering
• /
• v.26 no.1
• /
• pp.14-25
• /
• 2021

Change detection, which finds changes in remote sensing images of the same location captured at different times, is very important because it is used in various applications. However, registration errors, building displacement errors, and shadow errors cause false positives. To solve these problems, we propose a novle deep convolutional network called CADNet (Change Attention Dense Siamese Network). CADNet uses FPN (Feature Pyramid Network) to detect multi-scale changes, applies a Change Attention Module that attends to the changes, and uses DenseNet as a feature extractor to use feature maps that contain both low-level and high-level features for change detection. CADNet performance measured from the Precision, Recall, F1 side is 98.44%, 98.47%, 98.46% for WHU datasets and 90.72%, 91.89%, 91.30% for LEVIR-CD datasets. The results of this experiment show that CADNet can offer better performance than any other traditional change detection method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.4
• /
• pp.1714-1729
• /
• 2018

Change detection of remote sensing images is a profound challenge in the field of remote sensing image analysis. This paper proposes a novel change detection method for bitemporal remote sensing images based on feature fusion and fuzzy c-means (FCM). Different from the state-of-the-art methods that mainly utilize a single image feature for difference image construction, the proposed method investigates the fusion of multiple image features for the task. The subsequent problem is regarded as the difference image classification problem, where a modified fuzzy c-means approach is proposed to analyze the difference image. The proposed method has been validated on real bitemporal remote sensing data sets. Experimental results confirmed the effectiveness of the proposed method.

• Proceedings of the KSRS Conference
• /
• 2002.10a
• /
• pp.696-701
• /
• 2002

This paper describes some results of change detection in Tokyo metropolitan area, Japan , using the Landsat TM data, and methods to quantify the ground cover classes. The changes are analyzed using the measures of not only conventional spectral classes but also a set of landscape indices to describe spatial properties of ground cove types using fractal dimension of objects, entropy in the specific windows defining the neighbors of focusing locations. In order eliminate the seasonal radiometric effects on TM data, an automated class labeling method is also attempted. Urban areas are also delineated automatically by defining the boundaries of the urban area. These procedures for urban change detection were implemented by the unified image computing methods proposed by the author, they can be automated in coherent and systematic ways, and it is anticipated to automate the whole procedures. The results of this analysis suggest that Tokyo metropolitan area was extended to the suburban areas along the new transportation networks and the high density area of Tokyo were also very much extended during the period between 1985 and 1995.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.8 no.6
• /
• pp.1-8
• /
• 2000

A new method of knock detection in SI engines, using a change of ion concentration in the combustion chamber, was developed. In order to measure in-cylinder ionization current, ionization probes were installed at spark plug and cylinder head of production engine. It was found that the electric current generated by ionized gas in core burned gas region of knocking cycle is between 2 and 10 times larger than that of normal cycle, because the burned gas temperature which is the dominant parameter of a change of ion concentration increases. However, a change of ionization current in boundary region of burned gas is relatively weak. Hence a change of ion concentration in core burned gas region can be used for knock detection.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.10a
• /
• pp.250-251
• /
• 2013

In this paper, we would like to extract criminals doing this criminal offense to smoke in elevators. Extraction method detect difference value using modified color-$X^2$-test and it was normalized. Next, we find frames that has occurred scene change in successive frames using the four-step algorithm of scene change detection. Finally, we present the method of smoking image retrieval and extraction in stored large amount of video.

• Geophysics and Geophysical Exploration
• /
• v.2 no.3
• /
• pp.154-158
• /
• 1999

This paper introduces a partial edge detection technique, that improves the processing time of an automatic change tracking system for multi-temporal images. In the conventional change tracking systems for multi-temporal images, the edge detection is performed over the whole image. In the proposed method, however, the necessary portions for the edge detection is selected first and the edge detection is performed over the selected parts only. As a consequence, the improvement in the processing time could be achieved. The proposed change tracking system is expected to be utilized as a very efficient tool to configure changes in large data set such as remotely sensed satellite imagery or geophysical time laps images.

• The Journal of Information Systems
• /
• v.14 no.3
• /
• pp.117-122
• /
• 2005

This paper presents a method for detecting scene changes in video sequences, in which the $chi^{2}$-test is modified by imposing weights according to NTSC standard. To automatically determine threshold values for scene change detection, the proposed method utilizes the frame differences that are obtained by the weighted $chi^{2}$-test. In the first step, the mean and the standard deviation of the difference values are calculated, and then, we subtract the mean difference value from each difference value. In the next step, the same process is performed on the remained difference values, mean-subtracted frame differences, until the stopping criterion is satisfied. Finally, the threshold value for scene change detection is determined by the proposed automatic threshold estimation algorithm. The proposed method is tested on various video sources and, in the experimental results, it is shown that the proposed method is reliably estimates the thresholds and detects scene changes.

• Korean Journal of Remote Sensing
• /
• v.19 no.3
• /
• pp.263-269
• /
• 2003

This research examined the capabilities of KOMPSAT-1 EOC images for the application of urban environment, including the urban changes of the study areas. This research is constructed in three stages: Firstly, for the application of change detection techniques, which utilizes multi-temporal remotely sensed data, the data normalization process is carried out. Secondly, the change detection method is applied for the systematic monitoring of land-use changes. Lastly, using the results of the previous stages, the land-use map is updated. Consequently, the patterns of land-use changes are monitored by the proposed scheme. In this research, using the multi-temporal KOMPSAT-1 EOC images and land-use maps, monitoring of urban growth was carried out with the application of land-use changes, and the potential and scope of the application of the EOC images were also examined.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.10C
• /
• pp.983-991
• /
• 2005

Human faces are commonly found in a video such as a drama and provide useful information for video content analysis. Therefore, face detection plays an important role in applications such as face recognition, and face image database management. In this paper, we propose a face detection algorithm based on pre-processing of scene change detection for indexing and cast searching in video. The proposed algorithm consists of three stages: scene change detection stage, face region detection stage, and eyes and mouth detection stage. Experimental results show that the proposed algorithm can detect faces successfully over a wide range of facial variations in scale, rotation, pose, and position, and the performance is improved by $24\%$with profile images comparing with conventional methods using color components.

• Proceedings of the KSRS Conference
• /
• 2005.10a
• /
• pp.233-235
• /
• 2005

This paper presents an unsupervised change detection methodology designed for the detection of landslide areas. The proposed methodology consists of two analytical steps: one for multi-temporal segmentation and the other for automatic selection of thresholding values. By considering the conditions of landslide occurrences and the spectral behavior of multi-temporal remote sensing images, some specific procedures are included in the analytical steps mentioned above. The effectiveness and applicability of the methodology proposed here were illustrated by a case study of the Gangneung area, Korea. The case study demonstrated that the proposed methodology could detect about $83\%$ of landslide occurrences.