• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.12
• /
• pp.4795-4815
• /
• 2020

Drone detection can be considered as a specific sort of small object detection, which has always been a challenge because of its small size and few features. For improving the detection rate of drones, we design a Deeper SSD network, which uses large-scale input image and deeper convolutional network to obtain more features that benefit small object classification. At the same time, in order to improve object classification performance, we implemented the up-sampling modules to increase the number of features for the low-level feature map. In addition, in order to improve object location performance, we adopted the down-sampling modules so that the context information can be used by the high-level feature map directly. Our proposed Deeper SSD and its variants are successfully applied to the self-designed drone datasets. Our experiments demonstrate the effectiveness of the Deeper SSD and its variants, which are useful to small drone's detection and recognition. These proposed methods can also detect small and large objects simultaneously.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.8
• /
• pp.2688-2703
• /
• 2022

Research on the advanced detection of harmful objects in airport cargo for passenger safety against terrorism has increased recently. However, because associated studies are primarily focused on the detection of relatively large objects, research on the detection of small objects is lacking, and the detection performance for small objects has remained considerably low. Here, we verified the limitations of existing research on object detection and developed a new model called the Small Hazardous Object detection enhanced and reconstructed Model based on the You Only Look Once version 5 (YOLOv5) algorithm to overcome these limitations. We also examined the performance of the proposed model through different experiments based on YOLOv5, a recently launched object detection model. The detection performance of our model was found to be enhanced by 0.3 in terms of the mean average precision (mAP) index and 1.1 in terms of mAP (.5:.95) with respect to the YOLOv5 model. The proposed model is especially useful for the detection of small objects of different types in overlapping environments where objects of different sizes are densely packed. The contributions of the study are reconstructed layers for the Small Hazardous Object detection enhanced and reconstructed Model based on YOLOv5 and the non-requirement of data preprocessing for immediate industrial application without any performance degradation.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.1243-1244
• /
• 2022

In recent years, the growing interest in off-site construction has led to factories scaling up their manufacturing and production processes in the construction sector. Consequently, continuous large-scale site monitoring in low-variability environments, such as prefabricated components production plants (precast concrete production), has gained increasing importance. Although many studies on computer vision-based site monitoring have been conducted, challenges for deploying this technology for large-scale field applications still remain. One of the issues is collecting and transmitting vast amounts of video data. Continuous site monitoring systems are based on real-time video data collection and analysis, which requires excessive computational resources and network traffic. In addition, it is difficult to integrate various object information with different sizes and scales into a single scene. Various sizes and types of objects (e.g., workers, heavy equipment, and materials) exist in a plant production environment, and these objects should be detected simultaneously for effective site monitoring. However, with the existing object detection algorithms, it is difficult to simultaneously detect objects with significant differences in size because collecting and training massive amounts of object image data with various scales is necessary. This study thus developed a large-scale site monitoring system using edge computing and a small-object detection system to solve these problems. Edge computing is a distributed information technology architecture wherein the image or video data is processed near the originating source, not on a centralized server or cloud. By inferring information from the AI computing module equipped with CCTVs and communicating only the processed information with the server, it is possible to reduce excessive network traffic. Small-object detection is an innovative method to detect different-sized objects by cropping the raw image and setting the appropriate number of rows and columns for image splitting based on the target object size. This enables the detection of small objects from cropped and magnified images. The detected small objects can then be expressed in the original image. In the inference process, this study used the YOLO-v5 algorithm, known for its fast processing speed and widely used for real-time object detection. This method could effectively detect large and even small objects that were difficult to detect with the existing object detection algorithms. When the large-scale site monitoring system was tested, it performed well in detecting small objects, such as workers in a large-scale view of construction sites, which were inaccurately detected by the existing algorithms. Our next goal is to incorporate various safety monitoring and risk analysis algorithms into this system, such as collision risk estimation, based on the time-to-collision concept, enabling the optimization of safety routes by accumulating workers' paths and inferring the risky areas based on workers' trajectory patterns. Through such developments, this continuous large-scale site monitoring system can guide a construction plant's safety management system more effectively.

• Proceedings of the KIEE Conference
• /
• 1995.11a
• /
• pp.225-227
• /
• 1995

An object detection algorithm using a modified IDM(Image Differential Method) is proposed for detecting an object in a level crossing area. The conventional object detection method using LASER light has the deadzone that it cannot detect small objects, while the object detection method using image data in a level crossing area can detect such small objects. But the image data in a level crossing area can be changeable easily because the data is outdoor and sensitive to such surrounding environments as the change of the sun beam, the shadow of cars, and so on. So we resolve these problems by adding the normalization and the process for shadow of the image data in a level crossing area to the basic IDM(Image Differential Method).

• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.10a
• /
• pp.506-509
• /
• 2016

We present real-time pedestrian detection that exploit accuracy of Faster R-CNN network. Faster R-CNN has shown to success at PASCAL VOC multi-object detection tasks, and their ability to operate on raw pixel input without the need to design special features is very engaging. Therefore, in this work we apply and adjust Faster R-CNN to single object detection, which is pedestrian detection. The drawback of Faster R-CNN is its failure when object size is small. Previously, small sized object problem was solved by Scale-aware Network. We incorporate Scale-aware Network to Faster R-CNN. This made our method Scale-aware Faster R-CNN (DF R-CNN) that is both fast and very accurate. We separated Faster R-CNN networks into two sub-network, that is one for large-size objects and another one for small-size objects. The resulting approach achieves a 28.3% average miss rate on the Caltech Pedestrian detection benchmark, which is competitive with the other best reported results.

• ETRI Journal
• /
• v.42 no.2
• /
• pp.230-238
• /
• 2020

Human-object interaction (HOI) detection is a popular computer vision task that detects interactions between humans and objects. This task can be useful in many applications that require a deeper understanding of semantic scenes. Current HOI detection networks typically consist of a feature extractor followed by detection layers comprising small filters (eg, 1 × 1 or 3 × 3). Although small filters can capture local spatial features with a few parameters, they fail to capture larger context information relevant for recognizing interactions between humans and distant objects owing to their small receptive regions. Hence, we herein propose a three-stream HOI detection network that employs a context convolution module (CCM) in each stream branch. The CCM can capture larger contexts from input feature maps by adopting combinations of large separable convolution layers and residual-based convolution layers without increasing the number of parameters by using fewer large separable filters. We evaluate our HOI detection method using two benchmark datasets, V-COCO and HICO-DET, and demonstrate its state-of-the-art performance.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.4
• /
• pp.1989-2011
• /
• 2019

Vehicle detection based on aerial images is an interesting and challenging research topic. Most of the traditional vehicle detection methods are based on the sliding window search algorithm, but these methods are not sufficient for the extraction of object features, and accompanied with heavy computational costs. Recent studies have shown that convolutional neural network algorithm has made a significant progress in computer vision, especially Faster R-CNN. However, this algorithm mainly detects objects in natural scenes, it is not suitable for detecting small object in aerial view. In this paper, an accurate and effective vehicle detection algorithm based on Faster R-CNN is proposed. Our method fuse a hyperactive feature map network with Eltwise model and Concat model, which is more conducive to the extraction of small object features. Moreover, setting suitable anchor boxes based on the size of the object is used in our model, which also effectively improves the performance of the detection. We evaluate the detection performance of our method on the Munich dataset and our collected dataset, with improvements in accuracy and effectivity compared with other methods. Our model achieves 82.2% in recall rate and 90.2% accuracy rate on Munich dataset, which has increased by 2.5 and 1.3 percentage points respectively over the state-of-the-art methods.

• The Journal of Korea Robotics Society
• /
• v.17 no.4
• /
• pp.425-430
• /
• 2022

As robots are considered one of the mainstream digital transformations, robots with machine vision becomes a main area of study providing the ability to check what robots watch and make decisions based on it. However, it is difficult to find a small object in the image mainly due to the flaw of the most of visual recognition networks. Because visual recognition networks are mostly convolution neural network which usually consider local features. So, we make a model considering not only local feature, but also global feature. In this paper, we propose a detection method of a small marker on the object using deep learning and an algorithm that considers global features by combining Transformer's self-attention technique with a convolutional neural network. We suggest a self-attention model with new definition of Query, Key and Value for model to learn global feature and simplified equation by getting rid of position vector and classification token which cause the model to be heavy and slow. Finally, we show that our model achieves higher mAP than state of the art model YOLOr.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.9
• /
• pp.1330-1339
• /
• 2022

3D object detection generally aims to detect relatively large data such as automobiles, buses, persons, furniture, etc, so it is vulnerable to small object detection. In addition, in an environment with limited resources such as embedded devices, it is difficult to apply the model because of the huge amount of computation. In this paper, the accuracy of small object detection was improved by focusing on local features using only one layer, and the inference speed was improved through the proposed knowledge distillation method from large pre-trained network to small network and adaptive quantization method according to the parameter size. The proposed model was evaluated using SUN RGB-D Val and self-made apple tree data set. Finally, it achieved the accuracy performance of 62.04% at mAP@0.25 and 47.1% at mAP@0.5, and the inference speed was 120.5 scenes per sec, showing a fast real-time processing speed.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.01a
• /
• pp.71-75
• /
• 2009

In this paper, we present a real-time method to detect moving objects in a rotating and zooming camera. It is useful for camera surveillance of fixed but rotating camera, camera on moving car, and so on. We first compensate the global motion, and then exploit the displaced frame difference (DFD) to find the block-wise boundary. For robust detection, we propose a kind of image to combine the detections from consecutive frames. We use the block-wise detection to achieve the real-time speed, except the pixel-wise DFD. In addition, a fast block-matching algorithm is proposed to obtain local motions and then global affine motion. In the experimental results, we demonstrate that our proposed algorithm can handle the real-time detection of common object, small object, multiple objects, the objects in low-contrast environment, and the object in zooming camera.