• Journal of the Korea Convergence Society
• /
• v.12 no.12
• /
• pp.31-37
• /
• 2021

In this paper proposed a feature fusion and spatial attention-based modified YOLOv4S for small and occluded detection. Conventional YOLOv4S is a lightweight network and lacks feature extraction capability compared to the method of the deep network. The proposed method first combines feature maps of different scales with feature fusion to enhance semantic and low-level information. In addition expanding the receptive field with dilated convolution, the detection accuracy for small and occluded objects was improved. Second by improving the conventional spatial information with spatial attention, the detection accuracy of objects classified and occluded between objects was improved. PASCAL VOC and COCO datasets were used for quantitative evaluation of the proposed method. The proposed method improved mAP by 2.7% in the PASCAL VOC dataset and 1.8% in the COCO dataset compared to the Conventional YOLOv4S.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.7
• /
• pp.2154-2168
• /
• 2022

Our work addresses the issues associated with usage of the semantic features by Bag of Words model, which requires construction of the dictionary. Extracting the relevant features and clustering them into code book or dictionary is computationally intensive and requires large storage area. Hence we propose to use a simple distribution of multiple shape based features, which is a mixture of gradients, radius and slope angles requiring very less computational cost and storage requirements but can serve as an equivalent image representative. The experimental work conducted on PASCAL VOC 2007 dataset exhibits marginally closer performance in terms of accuracy with the Bag of Word model using Self Organizing Map for clustering and very significant computational gain.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.7
• /
• pp.816-822
• /
• 2016

Content-Based image retrieval is a method to search by image features such as local color, texture, and other image content information, which is different from conventional tag or labeled text-based searching. In real life data, the number of images having tags or labels is relatively small, so it is hard to search the relevant images with text-based approach. Existing image search method only based on image feature similarity has limited performance and does not ensure that the results are what the user expected. In this study, we propose and validate a machine learning based approach to improve the performance of the image search engine. We note that when users search relevant images with a query image, they would expect the retrieved images belong to the same category as that of the query. Image classification method is combined with the traditional image feature similarity method. The proposed method is extensively validated on a public PASCAL VOC dataset consisting of 11,530 images from 20 categories.

• Journal of Broadcast Engineering
• /
• v.25 no.3
• /
• pp.386-398
• /
• 2020

We developed an integrative annotation program that can perform data labeling process for deep learning models in object recognition. The program utilizes the basic GUI library of Python and configures crawler functions that allow data collection in real time. Retinanet was used to implement an automatic annotation function. In addition, different data labeling formats for Pascal-VOC, YOLO and Retinanet were generated. Through the experiment of the proposed method, a domestic vehicle image dataset was built, and it is applied to Retinanet and YOLO as the training and test set. The proposed system classified the vehicle model with the accuracy of about 94%.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.12 no.3
• /
• pp.451-456
• /
• 2017

Semantic segmentation, which is the most basic and complicated problem in computer vision, classifies each pixel of an image into a specific object and performs a task of specifying a label. MRF and CRF, which have been studied in the past, have been studied as effective methods for improving the accuracy of pixel level labeling. In this paper, we propose a semantic partitioning method that combines CNN, a kind of deep running, which is in the spotlight recently, and CRF, a probabilistic model. For learning and performance verification, Pascal VOC 2012 image database was used and the test was performed using arbitrary images not used for learning. As a result of the study, we showed better partitioning performance than existing semantic partitioning algorithm.

• Journal of Software Engineering Society
• /
• v.29 no.1
• /
• pp.13-21
• /
• 2020

As CNN model is applied to various domains such as image classification and object detection, the performance of CNN model which is used to safety critical system like autonomous vehicles should be reliable. To evaluate that CNN model can sustain the performance in various environments, we developed an image data augmentation apparatus which generates images that is changed background. If an image which contains object is entered into the apparatus, it extracts an object image from the entered image and generate s composed images by synthesizing the object image with collected background images. A s a method to evaluate a CNN model, the apparatus generate s new test images from original test images, and we evaluate the CNN model by the new test image. As a case study, we generated new test images from Pascal VOC2007 and evaluated a YOLOv3 model with the new images. As a result, it was detected that mAP of new test images is almost 0.11 lower than mAP of the original test images.

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.5
• /
• pp.195-204
• /
• 2018

In this paper, we propose both a new loss function and an online hard example mining scheme for improving the performance of single-stage object detectors which use deep convolutional neural networks. The proposed loss function and the online hard example mining scheme can not only overcome the problem of imbalance between the number of annotated objects and the number of background examples, but also improve the localization accuracy of each object. Therefore, the loss function and the mining scheme can provide intrinsically fast single-stage detectors with detection performance higher than or similar to that of two-stage detectors. In experiments conducted with the PASCAL VOC 2007 benchmark dataset, we show that the proposed loss function and the online hard example mining scheme can improve the performance of single-stage object detectors.

• Journal of Convergence for Information Technology
• /
• v.11 no.9
• /
• pp.28-34
• /
• 2021

In the case of object detection using deep learning, both accuracy and real-time are required. However, it is difficult to use a deep learning model that processes a large amount of data in a limited resource environment. To solve this problem, this paper proposes an object detection model for small embedded devices. Unlike the general detection model, the model size was minimized by using a structure in which the pre-trained feature extractor was removed. The structure of the model was designed by repeatedly stacking lightweight convolution blocks. In addition, the number of region proposals is greatly reduced to reduce detection overhead. The proposed model was trained and evaluated using the public dataset PASCAL VOC. For quantitative evaluation of the model, detection performance was measured with average precision used in the detection field. And the detection speed was measured in a Raspberry Pi similar to an actual embedded device. Through the experiment, we achieved improved accuracy and faster reasoning speed compared to the existing detection method.

• Journal of Digital Convergence
• /
• v.19 no.5
• /
• pp.307-313
• /
• 2021

In this paper, a lightweight network with fewer parameters compared to the existing object detection method is proposed. In the case of the currently used detection model, the network complexity has been greatly increased to improve accuracy. Therefore, the proposed network uses EfficientNet as a feature extraction network, and the subsequent layers are formed in a pyramid structure to utilize low-level detailed features and high-level semantic features. An attention process was applied between pyramid structures to suppress unnecessary noise for prediction. All computational processes of the network are replaced by depth-wise and point-wise convolutions to minimize the amount of computation. The proposed network was trained and evaluated using the PASCAL VOC dataset. The features fused through the experiment showed robust properties for various objects through a refinement process. Compared with the CNN-based detection model, detection accuracy is improved with a small amount of computation. It is considered necessary to adjust the anchor ratio according to the size of the object as a future study.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.06a
• /
• pp.32-34
• /
• 2019

최근 딥러닝 기반의 다양한 물체 검출 알고리즘이 제안되어 높은 성능을 보이고 있다. 본 논문은 이러한 딥러닝 기반 물체 검출의 성능을 향상시키기 위해 입력영상에서 추출된 특징 지도를 강화하는 비지역적 특징 융합과, 이를 이용한 물체 검출 기법을 제안한다. 제안 기법은 입력영상에서 CNN 을 통해 추출한 특징 지도를 비지역적 특징 강화 블록을 통해 강화한다. 해당 블록 내에서 입력된 특징 지도는 먼저 여러 리셉티브 필드를 갖는 특징 지도로 분기된다. 그리고 분기된 특징 지도들은 비지역적 특징 융합 모듈에 의해 융합되어 강화된다. 이러한 과정을 통해 강화된 특징 지도는 비지역적 문맥 정보가 강화된 특성을 가지며, 해당 특징 지도를 이용하여 최종적으로 물체 검출을 수행한다. Pascal VOC 공인 데이터세트를 통한 실험 결과, 제안 기법은 기존 비교 기법 대비 향상된 검출 성능을 보인다.