• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.3
• /
• pp.389-395
• /
• 2022

Because of improvement of deep learning techniques, deep learning using computer vision such as classification, detection and segmentation has also been used widely at many fields. Expecially, automatic driving is one of the major fields that applies computer vision systems. Also there are a lot of works and researches to combine multiple tasks in a single network. In this study, we propose the network that predicts the individual depth of pedestrians and vehicles. Proposed model is constructed based on YOLOv3 for object detection and Monodepth for depth estimation, and it process object detection and depth estimation consequently using encoder and decoder based on hard parameter sharing. We also used attention module to improve the accuracy of both object detection and depth estimation. Depth is predicted with monocular image, and is trained using self-supervised training method.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.12
• /
• pp.77-84
• /
• 2022

In this paper, we propose a Label Reassignment Strategy to improve the performance of an object detection algorithm. Our approach involves two stages: an inference stage and an assignment stage. In the inference stage, we perform multi-scale inference with predefined scale sizes on a trained model and re-infer masked images to obtain robust classification results. In the assignment stage, we calculate the IoU between bounding boxes to remove duplicates. We also check box and class occurrence between the detection result and annotation label to re-assign the dominant class type. We trained the YOLOX-L model with the re-annotated dataset to validate our strategy. The model achieved a 3.9% improvement in mAP and 3x better performance on AP_S compared to the model trained with the original dataset. Our results demonstrate that the proposed Label Reassignment Strategy can effectively improve the performance of an object detection model.

• Journal of the Institute of Convergence Signal Processing
• /
• v.22 no.1
• /
• pp.30-37
• /
• 2021

Accurate 3D object tracking with camera images is a key enabling technology for augmented reality applications. Motivated by the impressive success of convolutional neural networks (CNNs) in computer vision tasks such as image classification, object detection, image segmentation, recent studies for 3D object tracking have focused on leveraging deep learning. In this paper, we review deep learning approaches for 3D object tracking. We describe key methods in this field and discuss potential future research directions.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.5
• /
• pp.35-42
• /
• 2013

Shot boundary detection is an essential step for efficient browsing, sorting, and classification of video data. Robust shot detection method should overcome the disturbances caused by pixel brightness and object movement between frames. In this paper, two shot boundary detection methods are presented to address these problem by using segmentation, object movement, and pixel brightness. The first method is based on the histogram that reflects object movements and the morphological dilation operation that considers pixel brightness. The second method uses the pixel brightness information of segmented and whole blocks between frames. Experiments on digitized video data of National Archive of Korea show that the proposed methods outperforms the existing pixel-based and histogram-based methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.11
• /
• pp.4534-4555
• /
• 2015

We propose a robust object cataloging method using multiple locally distinct heterogeneous features for aiding image retrieval. Due to challenges such as variations in object size, orientation, illumination etc. object recognition is extraordinarily challenging problem. In these circumstances, we adapt local interest point detection method which locates prototypical local components in object imageries. In each local component, we exploit heterogeneous features such as gradient-weighted orientation histogram, sum of wavelet responses, histograms using different color spaces etc. and combine these features together to describe each component divergently. A global signature is formed by adapting the concept of bag of feature model which counts frequencies of its local components with respect to words in a dictionary. The proposed method demonstrates its excellence in classifying objects in various complex backgrounds. Our proposed local feature shows classification accuracy of 98% while SURF,SIFT, BRISK and FREAK get 81%, 88%, 84% and 87% respectively.

• Journal of Korea Multimedia Society
• /
• v.8 no.8
• /
• pp.1057-1068
• /
• 2005

This paper proposes a real-time face detection system which detects multiple faces from low resolution video such as web-camera video. First, It finds face region candidates by using AdaBoost based object detection method which selects a small number of critical features from a larger set. Next, it generates reduced feature vector for each face region candidate by using principle component analysis. Finally, it classifies if the candidate is a face or non-face by using SVM(Support Vector Machine) based binary classification. According to experiment results, the proposed method achieves real-time face detection from low resolution video. Also, it reduces the false detection rate than existing methods by using PCA and SVM based face classification step.

• The Plant Pathology Journal
• /
• v.39 no.4
• /
• pp.319-334
• /
• 2023

Plant disease is an important factor affecting crop yield. With various types and complex conditions, plant diseases cause serious economic losses, as well as modern agriculture constraints. Hence, rapid, accurate, and early identification of crop diseases is of great significance. Recent developments in deep learning, especially convolutional neural network (CNN), have shown impressive performance in plant disease classification. However, most of the existing datasets for plant disease classification are a single background environment rather than a real field environment. In addition, the classification can only obtain the category of a single disease and fail to obtain the location of multiple different diseases, which limits the practical application. Therefore, the object detection method based on CNN can overcome these shortcomings and has broad application prospects. In this study, an annotated apple leaf disease dataset in a real field environment was first constructed to compensate for the lack of existing datasets. Moreover, the Faster R-CNN and YOLOv3 architectures were trained to detect apple leaf diseases in our dataset. Finally, comparative experiments were conducted and a variety of evaluation indicators were analyzed. The experimental results demonstrate that deep learning algorithms represented by YOLOv3 and Faster R-CNN are feasible for plant disease detection and have their own strong points and weaknesses.

• Journal of Platform Technology
• /
• v.12 no.3
• /
• pp.62-70
• /
• 2024

Recent surveillance systems employ multiple sensors, such as cameras and radars, to enhance the accuracy of intrusion detection. However, object recognition through camera (RGB, Thermal) sensors may not always be accurate during nighttime, in adverse weather conditions, or when the intruder is camouflaged. In such situations, it is possible to detect intruders by utilizing the trajectories of objects extracted from camera or radar sensors. This paper proposes a method to detect intruders using only trajectory information in environments where object recognition is challenging. The proposed method involves training an LSTM-Attention based trajectory classification model using normal and abnormal (intrusion, loitering) trajectory data of animals and humans. This model is then used to identify abnormal human trajectories and perform intrusion detection. Finally, the validity of the proposed method is demonstrated through experiments using real data.

• Convergence Security Journal
• /
• v.23 no.5
• /
• pp.135-142
• /
• 2023

In addressing the prominent issues of climate change, resource scarcity, and environmental pollution associated with household waste, extensive research has been conducted on intelligent waste classification methods. These efforts range from traditional classification algorithms to machine learning and neural networks. However, challenges persist in effectively classifying waste in diverse environments and conditions due to insufficient datasets, increased complexity in neural network architectures, and performance limitations for real-world applications. Therefore, this paper proposes i-YOLOX as a solution for rapid classification and improved accuracy. The proposed model is evaluated based on network parameters, detection speed, and accuracy. To achieve this, a dataset comprising 10,000 samples of household waste, spanning 17 waste categories, is created. The i-YOLOX architecture is constructed by introducing the Involution channel convolution operator and the Convolution Branch Attention Module (CBAM) into the YOLOX structure. A comparative analysis is conducted with the performance of the existing YOLO architecture. Experimental results demonstrate that i-YOLOX enhances the detection speed and accuracy of waste objects in complex scenes compared to conventional neural networks. This confirms the effectiveness of the proposed i-YOLOX architecture in the detection and classification of multiple household waste objects.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.11
• /
• pp.43-52
• /
• 2014

In this paper, we propose the target detection method using image displacement, and classification method using SURF(Speeded Up Robust Features) feature points and BAS(Beam Angle Statistics) in infrared images. The SURF method that is a typical correspondence matching method in the area of image processing has been widely used, because it is significantly faster than the SIFT(Scale Invariant Feature Transform) method, and produces a similar performance. In addition, in most SURF based object recognition method, it consists of feature point extraction and matching process. In proposed method, it detects the target area using the displacement, and target classification is performed by using the geometry of SURF feature points. The proposed method was applied to the unmanned target detection/recognition system. The experimental results in virtual images and real images, we have approximately 73~85% of the classification performance.