• 대한원격탐사학회지
• /
• 제27권6호
• /
• pp.717-728
• /
• 2011

An efficient method for the unsupervised classification of high resolution imagery is suggested in this paper. It employs pixel-linking and merging based on the adjacency graph. The proposed algorithm uses the neighbor lines of 8 directions to include information in spatial proximity. Two approaches are suggested to employ neighbor lines in the linking. One is to compute the dissimilarity measure for the pixel-linking using information from the best lines with the smallest non. The other is to select the best directions for the dissimilarity measure by comparing the non-homogeneity of each line in the same direction of two adjacent pixels. The resultant partition of pixel-linking is segmented and classified by the merging based on the regional and spectral adjacency graphs. This study performed extensive experiments using simulation data and a real high resolution data of IKONOS. The experimental results show that the new approach proposed in this study is quite effective to provide segments of high quality for object-based analysis and proper land-cover map for high resolution imagery of urban area.

• 전기학회논문지
• /
• 제68권2호
• /
• pp.359-363
• /
• 2019

As commercial drones have been widely used, concerns for collision accidents with people and invading secured properties are emerging. The detection of drone is a challenging problem. The deep learning based object detection techniques for detecting drones have been applied, but limited to the specific cases such as detection of drones from bird and/or background. We have tried not only detection of drones, but classification of different drones with an end-to-end model. YOLOv2 is used as an object detection model. In order to supplement insufficient data by shooting drones, data augmentation from collected images is executed. Also transfer learning from ImageNet for YOLOv2 darknet framework is performed. The experimental results for drone detection with average IoU and recall are compared and analysed.

• 대한공간정보학회지
• /
• 제19권1호
• /
• pp.105-113
• /
• 2011

기존에 제작된 주제도는 중 저해상도 위성영상 기반으로 제작이 이루어져 위치정확도 및 표현되는 주제 정보의 정밀도가 낮다는 단점이 있다. 최근 촬영되고 있는 디지털항공사진영상은 흑백 및 컬러영역의 밴드와 산림판독이 가능한 근적외선 영역 밴드의 촬영이 가능하며, 고해상도 영상을 획득할 수 있어 정밀한 토지피복분류의 수행이 가능할 것으로 판단된다. 이에 본 논문에서는 디지털항공사진영상을 이용한 객체기반 토지피복분류 가능성 타진과 디지털항공사진영상의 활용성 제시를 위하여 동일한 지역의 GSD 0.12m급 디지털항공사진영상과 GSD 1m급 IKONOS 위성영상으로 객체기반 토지피복분류를 수행하였으며, 정사영상과 기존 중분류 토지피복도의 정성적 분석을 수행하였다. 또한, TTA(Training and Test Area) Mask를 생성하여 분류정확도를 분석하였으며, 영상을 대상으로 스크린디지타이징을 수행하여 분류면적의 비교를 통한 정확도를 분석하였다. 분석결과 디지털항공사진을 이용한 토지피복도 제작이 가능하였으며, 위성영상에 비해 세밀한 분류가 가능하였다.

• International Journal of Advanced Culture Technology
• /
• 제8권4호
• /
• pp.119-128
• /
• 2020

Object detection is an important field of computer vision and is applied to applications such as security, autonomous driving, and face recognition. Recently, as the application of artificial intelligence technology including deep learning has been applied in various fields, it has become a more powerful tool that can learn meaningful high-level, deeper features, solving difficult problems that have not been solved. Therefore, deep learning techniques are also being studied in the field of object detection, and algorithms with excellent performance are being introduced. In this paper, a deep learning-based object detection algorithm used to detect multiple objects in an image is investigated, and future development directions are presented.

• Journal of Electrical Engineering and Technology
• /
• 제13권6호
• /
• pp.2468-2478
• /
• 2018

We propose the Sparse Feature Convolutional Neural Network (SFCNN) to reduce the volume of convolutional neural networks (CNNs). Despite the superior classification performance of CNNs, their enormous network volume requires high computational cost and long processing time, making real-time applications such as online-training difficult. We propose an advanced network that reduces the volume of conventional CNNs by producing a region-based sparse feature map. To produce the sparse feature map, two complementary region-based value extraction methods, cluster max extraction and local value extraction, are proposed. Cluster max is selected as the main function based on experimental results. To evaluate SFCNN, we conduct an experiment with two conventional CNNs. The network trains 59 times faster and tests 81 times faster than the VGG network, with a 1.2% loss of accuracy in multi-class classification using the Caltech101 dataset. In vehicle classification using the GTI Vehicle Image Database, the network trains 88 times faster and tests 94 times faster than the conventional CNNs, with a 0.1% loss of accuracy.

• 한국측량학회:학술대회논문집
• /
• 한국측량학회 2007년도 춘계학술발표회 논문집
• /
• pp.183-186
• /
• 2007

Hyperspectral remote sensing data contain plenty of information about objects, which makes object classification more precise. Over the past several years, different algorithms for the classification of hyperspectral remote sensing images have been developed. In this study, we proposed method based on absorption band extraction and Gravity type model to solve hyperspectral image classification problem. In contrast to conventional methods that are based on correlation techniques, this method is simple and more effective. The proposed approach was tested to evaluate its effectiveness. The evaluation was done by comparing the results of preexiting SFF(Spectral Feature Fitting) classification method. The evaluation results showed the proposed approach has a good potential in the classification of hyperspectral images.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권12호
• /
• pp.6009-6027
• /
• 2019

Support vector machine (SVM) classifiers have been widely used for object detection. These methods usually locate the object by finding the region with maximal score in an image. With bag-of-features representation, the SVM score of an image region can be written as the sum of its inside feature-weights. As a result, the searching process can be executed efficiently by using strategies such as branch-and-bound. However, the feature-weight derived by optimizing region classification cannot really reveal the category knowledge of a feature-point, which could cause bad localization. In this paper, we represent a region in an image by a collection of local feature-points and determine the object by the region with the maximum posterior probability of belonging to the object class. Based on the Bayes' theorem and Naive-Bayes assumptions, the posterior probability is reformulated as the sum of feature-scores. The feature-score is manifested in the form of the logarithm of a probability ratio. Instead of estimating the numerator and denominator probabilities separately, we readily employ the density ratio estimation techniques directly, and overcome the above limitation. Experiments on a car dataset and PASCAL VOC 2007 dataset validated the effectiveness of our method compared to the baselines. In addition, the performance can be further improved by taking advantage of the recently developed deep convolutional neural network features.

• IEIE Transactions on Smart Processing and Computing
• /
• 제6권1호
• /
• pp.10-17
• /
• 2017

We propose classification algorithms for human and dog movement. The proposed algorithms use micro-Doppler signals obtained from humans and dogs moving in four different directions. A two-stage classifier based on a support vector machine (SVM) is proposed, which uses a radial-based function (RBF) kernel and $16^{th}$-order linear predictive code (LPC) coefficients as feature vectors. With the proposed algorithms, we obtain the best classification results when a first-level SVM classifies the type of movement, and then, a second-level SVM classifies the moving object. We obtain the correct classification probability 95.54% of the time, on average. Next, to deal with the difficult classification problem of human and dog running, we propose a two-layer convolutional neural network (CNN). The proposed CNN is composed of six ($6{\times}6$) convolution filters at the first and second layers, with ($5{\times}5$) max pooling for the first layer and ($2{\times}2$) max pooling for the second layer. The proposed CNN-based classifier adopts an auto regressive spectrogram as the feature image obtained from the $16^{th}$-order LPC vectors for a specific time duration. The proposed CNN exhibits 100% classification accuracy and outperforms the SVM-based classifier. These results show that the proposed classifiers can be used for human and dog classification systems and also for classification problems using data obtained from an ultra-wideband (UWB) sensor.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권3호
• /
• pp.1264-1286
• /
• 2018

In this paper, a novel background prior-based salient object detection framework is proposed to deal with images those are more complicated. We take the superpixels located in four borders into consideration and exploit a mechanism based on image boundary information to remove the foreground noises, which are used to form the background prior. Afterward, an initial foreground prior is obtained by selecting superpixels that are the most dissimilar to the background prior. To determine the regions of foreground and background based on the prior of them, a threshold is needed in this process. According to a fixed threshold, the remaining superpixels are iteratively assigned based on their proximity to the foreground or background prior. As the threshold changes, different foreground priors generate multiple different partitions that are assigned a likelihood of being foreground. Last, all segments are combined into a saliency map based on the idea of similarity voting. Experiments on five benchmark databases demonstrate the proposed method performs well when it compares with the state-of-the-art methods in terms of accuracy and robustness.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권12호
• /
• pp.4439-4455
• /
• 2021

Compared with two-stage object detection algorithms, one-stage algorithms provide a better trade-off between real-time performance and accuracy. However, these methods treat the intermediate features equally, which lacks the flexibility to emphasize meaningful information for classification and location. Besides, they ignore the interaction of contextual information from different scales, which is important for medium and small objects detection. To tackle these problems, we propose an image pyramid network based on dual attention mechanism (DAIPNet), which builds an image pyramid to enrich the spatial information while emphasizing multi-scale informative features based on dual attention mechanisms for one-stage object detection. Our framework utilizes a pre-trained backbone as standard detection network, where the designed image pyramid network (IPN) is used as auxiliary network to provide complementary information. Here, the dual attention mechanism is composed of the adaptive feature fusion module (AFFM) and the progressive attention fusion module (PAFM). AFFM is designed to automatically pay attention to the feature maps with different importance from the backbone and auxiliary network, while PAFM is utilized to adaptively learn the channel attentive information in the context transfer process. Furthermore, in the IPN, we build an image pyramid to extract scale-wise features from downsampled images of different scales, where the features are further fused at different states to enrich scale-wise information and learn more comprehensive feature representations. Experimental results are shown on MS COCO dataset. Our proposed detector with a 300 × 300 input achieves superior performance of 32.6% mAP on the MS COCO test-dev compared with state-of-the-art methods.