• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.634-636
• /
• 2023

Surveillance systems play a pivotal role in ensuring the safety and security of various environments, including public spaces, critical infrastructure, and private properties. However, detecting abnormal human behavior in lowlight conditions is a critical yet challenging task due to the inherent limitations of visual data acquisition in such scenarios. This paper introduces a spatiotemporal framework designed to address the unique challenges posed by low-light environments, enhancing the accuracy and efficiency of human abnormality detection in surveillance camera systems. We proposed the pre-processing using lightweight exposure correction, patched frames pose estimation, and optical flow to extract the human behavior flow through t-seconds of frames. After that, we train the estimated-action-flow into autoencoder for abnormal behavior classification to get normal loss as metrics decision for normal/abnormal behavior.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.8
• /
• pp.2067-2081
• /
• 2024

Recently, image analysis research has been actively conducted due to the accumulation of big image data and the development of deep learning. Image analytics research has different characteristics from other data such as data size, real-time, image quality diversity, structural complexity, and security issues. In addition, a large amount of data is required to effectively analyze images with deep-learning models. However, in many fields, the data that can be collected is limited, so there is a need for meta learning based image analysis technology that can effectively train models with a small amount of data. This paper presents a comprehensive survey of meta-learning-based object-tracking techniques. This approach comprehensively explores object tracking methods and research that can achieve high performance in data-limited situations, including key challenges and future directions. It provides useful information for researchers in the field and can provide insights into future research directions.

• Smart Structures and Systems
• /
• v.29 no.4
• /
• pp.625-640
• /
• 2022

Maglev rail joints are vital components serving as connections between the adjacent F-type rail sections in maglev guideway. Damage to maglev rail joints such as bolt looseness may result in rough suspension gap fluctuation, failure of suspension control, and even sudden clash between the electromagnets and F-type rail. The condition monitoring of maglev rail joints is therefore highly desirable to maintain safe operation of maglev. In this connection, an online damage detection approach based on three-dimensional (3D) convolutional neural network (CNN) and time-frequency characterization is developed for simultaneous detection of multiple damage of maglev rail joints in this paper. The training and testing data used for condition evaluation of maglev rail joints consist of two months of acceleration recordings, which were acquired in-situ from different rail joints by an integrated online monitoring system during a maglev train running on a test line. Short-time Fourier transform (STFT) method is applied to transform the raw monitoring data into time-frequency spectrograms (TFS). Three CNN architectures, i.e., small-sized CNN (S-CNN), middle-sized CNN (M-CNN), and large-sized CNN (L-CNN), are configured for trial calculation and the M-CNN model with excellent prediction accuracy and high computational efficiency is finally optioned for multiple damage detection of maglev rail joints. Results show that the rail joints in three different conditions (bolt-looseness-caused rail step, misalignment-caused lateral dislocation, and normal condition) are successfully identified by the proposed approach, even when using data collected from rail joints from which no data were used in the CNN training. The capability of the proposed method is further examined by using the data collected after the loosed bolts have been replaced. In addition, by comparison with the results of CNN using frequency spectrum and traditional neural network using TFS, the proposed TFS-CNN framework is proven more accurate and robust for multiple damage detection of maglev rail joints.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.9
• /
• pp.4171-4176
• /
• 2012

The conventional block systems for railway signaling currently in operation in Korea have not been electrified or integrated and therefore there have been difficulties in terms of construction and maintenance. Two independent systems have been installed for ABS and LEU of ATP system (for speeded-up lines), although they deal with the same signaling information at the same location in order to control the trains. In these conventional ABS and LEU, a number of duplicate modules are installed in each device including lamp detection units and power supply units and it results increased manufacturing costs and maintenance efforts. This paper deals with the prototype development of integrated electronic block system with CPU-based digital control methods in order to overcome the limitations of the conventional ABS. The suggested system is the integration of the conventional ABS with LEU of ATP and it is also applicable for the non-ATP sections as well.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.37 no.6
• /
• pp.64-72
• /
• 2000

This paper deals with the parallel operation of two PWM converters for auxiliary block of high speed train. The parallel operation of AC/DC PWM converter controlled by 3-level PWM switching method to operate switching devices to realize a high power factor and reduce the primary side of the transformer current harmonics is proposed. In this paper, it is presented the phase shift technique between two converters switching phase, solution to eliminate the coupling effects due to the transformer and zero crossing detection method for synchronized with the source and controller. Experimental results for laboratory system with TMS320C31 microprocessor and 10［kVA］PWM converter confirm the validity of the proposed algorithm.

• Journal of the Korean Society for Railway
• /
• v.8 no.2
• /
• pp.145-154
• /
• 2005

Traffic accidents at highway-rail crossing result in larger social and economic damages than the accidents at the typical highway intersections. The traditional control and warning systems of the highway-rail crossing have limitations in that 1) they do not recognize the differences of the trains' arrival times because they rely on the distance-based control system, rather than the time-based one, and 2) thereby they usually cause longer delays of vehicles and pedestrians at the highway-rail crossings. The objective of this study is to develop a time-based railroad crossing control system which takes into account the speed and expected arrival time of trains. using the spot speeds and acceleration rates of trains measured at three points, the developed system was found to be able to accurately estimate the arrival time of train. VISSIM simulation package was utilized to compare system effect of the developed time-based railroad crossing control system with that of the conventional distance-based one. It was found that the developed time-based railroad crossing control system reduced the average travel time, maximum delay length, average delay time, and average number of stop-experienced vehicles as much as 7.0$\%$, 75.6$\%$, 12.7$\%$, and 60.0$\%$, respectively, compared with those from the conventional distance-based one.

• Journal of the Korean Society for Railway
• /
• v.13 no.5
• /
• pp.500-503
• /
• 2010

Until now, the track circuit with railroad which is a part of an electrical circuit wad used only for the detection of the train location, but as train speed is up to be higher, in order to overcome the limits of ground signal system the railway signal system has changed from the ground signal system to a cab signal system. The power source of the track circuit has also changed from a direct current or a high voltage impulse to an alternating current with high frequency which is a part of the audio frequency. To improve the maintenanability and according to the environment condition, the railway roadbed is rapidly changed to the ferroconcrete roadbed. In case of a track circuit to use an alternating current with high frequency as power source at a ferroconcrete roadbed, the characteristic of the track circuit is brought on a change from a loss of the magnetic combination instead of a leakage current from electric insulation which was caused by the reinforcing iron pod with lattice shape for durability. This paper is shown the influence and the loss of the signal current at AF track circuit on a ferroconcrete in the simulation sheets and presented a proposal for the preventive method from reduction of signal current.

• Journal of Information Processing Systems
• /
• v.16 no.1
• /
• pp.6-29
• /
• 2020

Biometrics identification using multiple modalities has attracted the attention of many researchers as it produces more robust and trustworthy results than single modality biometrics. In this paper, we present a novel multimodal recognition system that trains a deep learning network to automatically learn features after extracting multiple biometric modalities from a single data source, i.e., facial video clips. Utilizing different modalities, i.e., left ear, left profile face, frontal face, right profile face, and right ear, present in the facial video clips, we train supervised denoising auto-encoders to automatically extract robust and non-redundant features. The automatically learned features are then used to train modality specific sparse classifiers to perform the multimodal recognition. Moreover, the proposed technique has proven robust when some of the above modalities were missing during the testing. The proposed system has three main components that are responsible for detection, which consists of modality specific detectors to automatically detect images of different modalities present in facial video clips; feature selection, which uses supervised denoising sparse auto-encoders network to capture discriminative representations that are robust to the illumination and pose variations; and classification, which consists of a set of modality specific sparse representation classifiers for unimodal recognition, followed by score level fusion of the recognition results of the available modalities. Experiments conducted on the constrained facial video dataset (WVU) and the unconstrained facial video dataset (HONDA/UCSD), resulted in a 99.17% and 97.14% Rank-1 recognition rates, respectively. The multimodal recognition accuracy demonstrates the superiority and robustness of the proposed approach irrespective of the illumination, non-planar movement, and pose variations present in the video clips even in the situation of missing modalities.

• Journal of Broadcast Engineering
• /
• v.27 no.3
• /
• pp.283-294
• /
• 2022

The feature map used in the network for deep learning generally has larger data than the image and a higher compression rate than the image compression rate is required to transmit the feature map. This paper proposes a method for transmitting a pyramid feature map with high compression rate, which is used in a network with an FPN structure that has robustness to object size in deep learning-based image processing. In order to efficiently compress the pyramid feature map, this paper proposes a structure that predicts a pyramid feature map of a level that is not transmitted with pyramid feature map of some levels that transmitted through the proposed prediction network to efficiently compress the pyramid feature map and restores compression damage through the proposed reconstruction network. Suggested mAP, the performance of object detection for the COCO data set 2017 Train images of the proposed method, showed a performance improvement of 31.25% in BD-rate compared to the result of compressing the feature map through VTM12.0 in the rate-precision graph, and compared to the method of performing compression through PCA and DeepCABAC, the BD-rate improved by 57.79%.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.5
• /
• pp.274-286
• /
• 2022

Multi-object tracking has been studied for a long time under computer vision and plays a critical role in applications such as autonomous driving and driving assistance. Multi-object tracking techniques generally consist of a detector that detects objects and a tracker that tracks the detected objects. Various publicly available datasets allow us to train a detector model without much effort. However, there are relatively few publicly available datasets for training a tracker model, and configuring own tracker datasets takes a long time compared to configuring detector datasets. Hence, the detector is often developed separately with a tracker module. However, the separated tracker should be adjusted whenever the former detector model is changed. This study proposes a system that can train a model that performs detection and tracking simultaneously using only the detector training datasets. In particular, a Siam network with augmentation is used to compose the detector and tracker. Experiments are conducted on public datasets to verify that the proposed algorithm can formulate a real-time multi-object tracker comparable to the state-of-the-art tracker models.