• Journal of the Korea Society of Computer and Information
• /
• v.21 no.11
• /
• pp.31-38
• /
• 2016

In this paper, we propose multi-scale infrared target detection algorithm with varied filter size using integral image. Filter based target detection is widely used for small target detection, but it doesn't suit for large target detection depending on the filter size. When there are multi-scale targets on the sky background, detection filter with small filter size can not detect the whole shape of the large targe. In contrast, detection filter with large filter size doesn't suit for small target detection, but also it requires a large amount of processing time. The proposed algorithm integrates the filtering results of varied filter size for the detection of small and large targets. The proposed algorithm has good performance for both small and large target detection. Furthermore, the proposed algorithm requires a less processing time, since it use the integral image to make the mean images with different filter sizes for subtraction between the original image and the respective mean image. In addition, we propose the implementation of real-time embedded system using FPGA.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.12 no.4
• /
• pp.231-238
• /
• 2017

Detecting small infrared targets from the low-SCR images at a long distance is very hard. The previous Local Contrast Method (LCM) algorithm based on the human visual system shows a superior performance of detecting small targets by a background suppression technique through local contrast measure. However, its slow processing speed due to the heavy multi-scale processing overhead is not suitable to a variety of real-time applications. This paper presents a lightweight real-time small target detection algorithm, called by the Improved Selective Local Contrast Method (ISLCM), to reduce the scale-invariant computational overhead. The proposed ISLCM applies the improved local contrast measure to the predicted selective region so that it may have a comparable detection performance as the previous LCM while guaranteeing low scale-invariant computational load by exploiting both adaptive scale estimation and small target feature feasibility. Experimental results show that the proposed algorithm can reduce its computational overhead considerably while maintaining its detection performance compared with the previous LCM.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.05a
• /
• pp.358-361
• /
• 2021

In order to improve the accuracy of small target detection more effectively, this paper proposes an improved single shot detector (SSD) target detection and recognition method based on cspdarknet53, which introduces lightweight ECA attention mechanism and Feature Pyramid Network (FPN). First, the original SSD backbone network is replaced with cspdarknet53 to enhance the learning ability of the network. Then, a lightweight ECA attention mechanism is added to the basic convolution block to optimize the network. Finally, FPN is used to gradually fuse the multi-scale feature maps used for detection in the SSD from the deep to the shallow layers of the network to improve the positioning accuracy and classification accuracy of the network. Experiments show that the proposed target detection algorithm has better detection accuracy, and it improves the detection accuracy especially for small targets.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.4
• /
• pp.980-997
• /
• 2024

To improve the brightness of images and reveal hidden information in dark areas is the main objective of low-light image enhancement (LLIE). LLIE methods based on deep learning show good performance. However, there are some limitations to these methods, such as the complex network model requires highly configurable environments, and deficient enhancement of edge details leads to blurring of the target content. Single-scale feature extraction results in the insufficient recovery of the hidden content of the enhanced images. This paper proposed an edge detection-based multi-scale feature enhancement network for LLIE (EDMFEN). To reduce the loss of edge details in the enhanced images, an edge extraction module consisting of a Sobel operator is introduced to obtain edge information by computing gradients of images. In addition, a multi-scale feature enhancement module (MSFEM) consisting of multi-scale feature extraction block (MSFEB) and a spatial attention mechanism is proposed to thoroughly recover the hidden content of the enhanced images and obtain richer features. Since the fused features may contain some useless information, the MSFEB is introduced so as to obtain the image features with different perceptual fields. To use the multi-scale features more effectively, a spatial attention mechanism module is used to retain the key features and improve the model performance after fusing multi-scale features. Experimental results on two datasets and five baseline datasets show that EDMFEN has good performance when compared with the stateof-the-art LLIE methods.

• Journal of the Korea Society of Computer and Information
• /
• v.8 no.2
• /
• pp.31-36
• /
• 2003

This paper proposes an acceleration method of PCA(Principal Component Analysis) based feature detection. The feature detection method makes decision whether the target feature is included in a given image, and if included, calculates the position and extent of the target feature. The position and scale of the target feature or face is not known previously, all the possible locations should be tested for various scales to detect the target. This is a search Problem in huge search space. This Paper proposes a fast face and feature detection method by reducing the search space using the multi-stage prediction map and contour Prediction map. A Proposed method compared to the existing whole search way, and it was able to reduce a computational complexity below 10％ by experiment.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.7
• /
• pp.2328-2344
• /
• 2022

2D human pose estimation still faces difficulty in low-resolution images. Most existing top-down approaches scale up the target human bonding box images to the large size and insert the scaled image into the network. Due to up-sampling, artifacts occur in the low-resolution target images, and the degraded images adversely affect the accurate estimation of the joint positions. To address this issue, we propose a multi-resolution input feature fusion network for human pose estimation. Specifically, the bounding box image of the target human is rescaled to multiple input images of various sizes, and the features extracted from the multiple images are fused in the network. Moreover, we introduce a guiding channel which induces the multi-resolution input features to alternatively affect the network according to the resolution of the target image. We conduct experiments on MS COCO dataset which is a representative dataset for 2D human pose estimation, where our method achieves superior performance compared to the strong baseline HRNet and the previous state-of-the-art methods.

• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.64 no.3
• /
• pp.187-192
• /
• 2015

Detecting human in images is a challenging task owing to their variable appearance and the wide range of poses the they can adopt. The first need is a robust feature set that allows the human form to be discriminated cleanly, even in cluttered background under difficult illumination. A large number of vision application rely on matching keypoints across images. These days, the deployment of vision algorithms on smart phones and embedded device with low memory and computation complexity has even upped the ante: the goal is to make descriptors faster compute, more compact while remaining robust scale, rotation and noise. In this paper we focus on improving the speed of pedestrian(walking person) detection using Histogram of Oriented Gradient(HOG) descriptors provide excellent performance and tracking using kalman filter.

• Journal of Information Processing Systems
• /
• v.16 no.4
• /
• pp.795-808
• /
• 2020

Due to the poor evaluation indexes such as detection accuracy and recall rate when Yolov3 network detects aircraft in remote sensing images, in this paper, we propose a remote sensing image aircraft detection method based on machine vision. In order to improve the target detection effect, the Inception module was introduced into the Yolov3 network structure, and then the data set was cluster analyzed using the k-means algorithm. In order to obtain the best aircraft detection model, on the basis of our proposed method, we adjusted the network parameters in the pre-training model and improved the resolution of the input image. Finally, our method adopted multi-scale training model. In this paper, we used remote sensing aircraft dataset of RSOD-Dataset to do experiments, and finally proved that our method improved some evaluation indicators. The experiment of this paper proves that our method also has good detection and recognition ability in other ground objects.

• Journal of Institute of Control, Robotics and Systems
• /
• v.13 no.11
• /
• pp.1074-1081
• /
• 2007

This paper presents a method for real-time face detection and tracking which combined Adaboost and Camshift algorithm. Adaboost algorithm is a method which selects an important feature called weak classifier among many possible image features by tuning weight of each feature from learning candidates. Even though excellent performance extracting the object, computing time of the algorithm is very high with window size of multi-scale to search image region. So direct application of the method is not easy for real-time tasks such as multi-task OS, robot, and mobile environment. But CAMshift method is an improvement of Mean-shift algorithm for the video streaming environment and track the interesting object at high speed based on hue value of the target region. The detection efficiency of the method is not good for environment of dynamic illumination. We propose a combined method of Adaboost and CAMshift to improve the computing speed with good face detection performance. The method was proved for real image sequences including single and more faces.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.10
• /
• pp.5095-5111
• /
• 2019

A multi-rotor Unmanned Aerial Vehicle (UAV) system is developed to solve the manhole cover detection problem for the infrastructure maintenance in the suburbs of big city. The visible light sensor is employed to collect the ground image data and a series of image processing and machine learning methods are used to detect the manhole cover. First, the image enhancement technique is employed to improve the imaging effect of visible light camera. An imaging environment perception method is used to increase the computation robustness: the blind Image Quality Evaluation Metrics (IQEMs) are used to percept the imaging environment and select the images which have a high imaging definition for the following computation. Because of its excellent processing effect the adaptive Multiple Scale Retinex (MSR) is used to enhance the imaging quality. Second, the Single Shot multi-box Detector (SSD) method is utilized to identify the manhole cover for its stable processing effect. Third, the spatial coordinate of manhole cover is also estimated from the ground image. The practical applications have verified the outdoor environment adaptability of proposed algorithm and the target detection correctness of proposed system. The detection accuracy can reach 99% and the positioning accuracy is about 0.7 meters.