• International Journal of Internet, Broadcasting and Communication
• /
• v.13 no.2
• /
• pp.156-165
• /
• 2021

In this paper, we propose an histogram weighted centroid based Siamese region proposal network for object tracking. The original Siamese region proposal network uses two identical artificial neural networks which take two different images as the inputs and decide whether the same object exist in both input images based on a similarity measure. However, as the Siamese network is pre-trained offline, it experiences many difficulties in the adaptation to various online environments. Therefore, in this paper we propose to incorporate the histogram weighted centroid feature into the Siamese network method to enhance the accuracy of the object tracking. The proposed method uses both the histogram information and the weighted centroid location of the top 10 color regions to decide which of the proposed region should become the next predicted object region.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.4
• /
• pp.1795-1811
• /
• 2019

In order to achieve rapid and accurate detection of vehicle objects in complex traffic conditions, we propose a novel vehicle detection method. Firstly, more contextual and small-object vehicle information can be obtained by our Joint Feature Network (JFN). Secondly, our Evolved Region Proposal Network (EPRN) generates initial anchor boxes by adding an improved version of the region proposal network in this network, and at the same time filters out a large number of false vehicle boxes by soft-Non Maximum Suppression (NMS). Then, our Mask Network (MaskN) generates an example that includes the vehicle occlusion, the generator and discriminator can learn from each other in order to further improve the vehicle object detection capability. Finally, these candidate vehicle detection boxes are optimized to obtain the final vehicle detection boxes by the Fine-Tuning Network(FTN). Through the evaluation experiment on the DETRAC benchmark dataset, we find that in terms of mAP, our method exceeds Faster-RCNN by 11.15%, YOLO by 11.88%, and EB by 1.64%. Besides, our algorithm also has achieved top2 comaring with MS-CNN, YOLO-v3, RefineNet, RetinaNet, Faster-rcnn, DSSD and YOLO-v2 of vehicle category in KITTI dataset.

• Journal of Korea Multimedia Society
• /
• v.20 no.8
• /
• pp.1271-1281
• /
• 2017

It is essential to collect and analyze target information around the vehicle for autonomous driving of the vehicle. Based on the analysis, environmental information such as location and direction should be analyzed in real time to control the vehicle. In particular, obstruction or cutting of objects in the image must be handled to provide accurate information about the vehicle environment and to facilitate safe operation. In this paper, we propose a method to simultaneously generate 2D and 3D bounding box proposals using LiDAR Edge generated by filtering LiDAR sensor information. We classify the classes of each proposal by connecting them with Region-based Fully-Covolutional Networks (R-FCN), which is an object classifier based on Deep Learning, which uses two-dimensional images as inputs. Each 3D box is rearranged by using the class label and the subcategory information of each class to finally complete the 3D bounding box corresponding to the object. Because 3D bounding boxes are created in 3D space, object information such as space coordinates and object size can be obtained at once, and 2D bounding boxes associated with 3D boxes do not have problems such as occlusion.

• Journal of Korea Multimedia Society
• /
• v.25 no.2
• /
• pp.247-256
• /
• 2022

Visual tracking of selected target objects is fundamental challenging problems in computer vision. Object tracking localize the region of target object with bounding box in the video. We propose a Siam-FPN based custom fully CNN to solve visual tracking problems by regressing the target area in an end-to-end manner. A method of preserving the feature information flow using a feature map connection structure was applied. In this way, information is preserved and emphasized across the network. To regress object region and to classify object, the region proposal network was connected with the Siamese network. The performance of the tracking algorithm was evaluated using the OTB-100 dataset. Success Plot and Precision Plot were used as evaluation matrix. As a result of the experiment, 0.621 in Success Plot and 0.838 in Precision Plot were achieved.

• Journal of Communications and Networks
• /
• v.18 no.1
• /
• pp.112-122
• /
• 2016

Cognitive radio (CR) is considered an attractive technology to deal with the spectrum scarcity problem. Multi-radio access technology (multi-RAT) can improve network capacity because data are transmitted by multiple RANs (radio access networks) concurrently. Thus, multi-RAT embedded in a cognitive radio network (CRN) is a promising paradigm for developing spectrum efficiency and network capacity in future wireless networks. In this study, we consider a new CRN model in which the primary user networks consist of heterogeneous primary users (PUs). Specifically, we focus on the energy-efficient resource allocation (EERA) problem for CR users with a special location coverage overlapping region in which heterogeneous PUs operate simultaneously via multi-RAT. We propose a two-tier crossover genetic algorithm-based search scheme to obtain an optimal solution in terms of the power and bandwidth. In addition, we introduce a radio environment map to manage the resource allocation and network synchronization. The simulation results show the proposed algorithm is stable and has faster convergence. Our proposal can significantly increase the energy efficiency.

• International Journal of Advanced Culture Technology
• /
• v.9 no.3
• /
• pp.305-314
• /
• 2021

Currently, due to COVID-19, household waste has a lot of impact on the environment due to packaging of food delivery. In this paper, we design and implement Faster-RCNN, SSD, and YOLOv4 models for municipal waste detection and classification. The data set explores two types of plastics, which account for a large proportion of household waste, and the types of aluminum cans. To classify the plastic type and the aluminum can type, 1,083 aluminum can types and 1,003 plastic types were studied. In addition, in order to increase the accuracy, we compare and evaluate the loss value and the accuracy value for the detection of municipal waste classification using Faster-RCNN, SDD, and YoloV4 three models. As a final result of this paper, the average precision value of the SSD model is 99.99%, the average precision value of plastics is 97.65%, and the mAP value is 99.78%, which is the best result.

• Journal of Korea Multimedia Society
• /
• v.25 no.1
• /
• pp.72-81
• /
• 2022

Visual Object Tracking is known as the most fundamental problem in the field of computer vision. Object tracking localize the region of target object with bounding box in the video. In this paper, a custom CNN is created to extract object feature that has strong and various information. This network was constructed as a Siamese network for use as a feature extractor. The input images are passed convolution block composed of a bottleneck layers, and features are emphasized. The feature map of the target object and the search area, extracted from the Siamese network, was input as a local proposal network. Estimate the object area using the feature map. The performance of the tracking algorithm was evaluated using the OTB2013 dataset. Success Plot and Precision Plot were used as evaluation matrix. As a result of the experiment, 0.611 in Success Plot and 0.831 in Precision Plot were achieved.

• Proceedings of the KSR Conference
• /
• 2006.11b
• /
• pp.1029-1036
• /
• 2006

South and North Koreas are putting forth efforts to overcome the distrust and animosity of the past 50 years to open an era of harmony and cooperation where the two halves can work together for mutual benefits. As part of those efforts, both parties are working now to reconnect the railways between the North and the South that remained broken for the past 60 years. In addition, the restoration of Trans-Korean railway paves the way for the "Silk Road Railway" which links European continent to Asian regions and Pacific Rim. The restoration project acts as a conduit for cooperation within in the Northeast Asian continent, hence, an important tool for facilitating peace and prosperity within the Northeast Asian region. Notably, the Railway project is regarded as the cardinal future-oriented peace building project for cultivating constructive, cooperative relations (Trans-Korean Railway and Trans-Asian Railway works) by stimulating human resources and commodity flows through railroad transportations. Northeast Asian region takes on a similar instance to the unification of European continent through its astounding development in railroad transportation, i.e., the international re-construction of Railroad lines will act as a catalyst to link Eurasian areas into one regional community for cooperation and peace. At present, the government is creating a momentum to bind trans-Eurasian railroad works and an initiative for "Northeast Asia Railroad networks and consultative organization". The South Korean administration paves the way to develop railroad network within South-North Korean, Russia and Eurasian region. It also fosters railroad cooperation with China for people and goods transports. To achieve such objectives, the project requires wide publicity and cross-border cooperation from concerned countries. The blueprint would have to be drafted up for Northeast Asian railroad train demonstration runs, Northeast Asian transportation agreements, with a bid to promote constitute Northeast Asian Railroad Consultation body. Moreover, the government would also have to prepare both, a draft of the linkage and the mandated standardized proposal.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.2
• /
• pp.855-870
• /
• 2020

Windows are key components of building facades. Detecting windows, crucial to 3D semantic reconstruction and scene parsing, is a challenging task in computer vision. Early methods try to solve window detection by using hand-crafted features and traditional classifiers. However, these methods are unable to handle the diversity of window instances in real scenes and suffer from heavy computational costs. Recently, convolutional neural networks based object detection algorithms attract much attention due to their good performances. Unfortunately, directly training them for challenging window detection cannot achieve satisfying results. In this paper, we propose an approach for window detection. It involves an improved Faster R-CNN architecture for window detection, featuring in a window region proposal network, an RoI feature fusion and a context enhancement module. Besides, a post optimization process is designed by the regular distribution of windows to refine detection results obtained by the improved deep architecture. Furthermore, we present a newly collected dataset which is the largest one for window detection in real street scenes to date. Experimental results on both existing datasets and the new dataset show that the proposed method has outstanding performance.

• The Journal of the Acoustical Society of Korea
• /
• v.40 no.5
• /
• pp.466-472
• /
• 2021

Speaker Change Detection (SCD) refers to finding the moment when the main speaker changes from one person to the next in a speech conversation. In speaker change detection, difficulties arise due to overlapping speakers, inaccuracy in the information labeling, and data imbalance. To solve these problems, TIMIT corpus widely used in speech recognition have been concatenated artificially to obtain a sufficient amount of training data, and the detection of changing speaker has performed after identifying overlapping speakers. In this paper, we propose an speaker change detection system that considers the speaker overlapping. We evaluated and verified the performance using various approaches. As a result, a detection system similar to the X-Vector structure was proposed to remove the speaker overlapping region, while the Bi-LSTM method was selected to model the speaker change system. The experimental results show a relative performance improvement of 4.6 % and 13.8 % respectively, compared to the baseline system. Additionally, we determined that a robust speaker change detection system can be built by conducting related studies based on the experimental results, taking into consideration text and speaker information.