Autonomous Vision-based Target Detection and Safe Landing for UAV

Mohammed Rabah,Ali Rohan,Muhammad Talha,남강현,김성호 제어·로봇·시스템학회 2018 International Journal of Control, Automation, and Vol.16 No.6

Target detection is crucial for many applications of Unmanned Aerial Vehicles (UAVs) such as search and rescue, object transportation, object detection, inspection, and mapping. One of the considerable applications of target detection is the safe landing of UAV to the drone station for battery charging and its maintenance. For this, vision-based target detection methods are utilized. Generally, high-cost cameras and expensive CPU’'s were used for target detection. With the recent development of Raspberry Pi (RPi), it is possible to use the embeddedsystem with cheap price for such applications. In the current research, RPi based drone target detection and safe landing system are proposed with the integration of PID controller for target detection, and Fuzzy Logic controller for safe landing. The proposed system is equipped with a USB camera which is connected to RPi for detecting the target and a laser rangefinder (LIDAR) for measuring the distance for safe landing. To verify the performance of the developed system, a practical test bench based on a quadcopter and a target drone station is developed. Severalexperiments were conducted under different scenarios. The result shows that the proposed system works well for the target finding and safe landing of the quadcopter.

Research on Target Characteristics and Target Recognition Algorithm under Complex Background

Mianmian Dong,Baoyi Guo 보안공학연구지원센터 2016 International Journal of Hybrid Information Techno Vol.9 No.5

To improve the recognition rate of dynamic target under complex background, this paper studied the target characteristics and recognition algorithm of moving target. According to the light intensity, target shape and motion characteristics, the calculation model of the target characteristics was established, the optical radiation characteristic and the detection performance of photoelectric detection system under complex background were analyzed. By means of image segmentation and mathematical morphology transform, the target information extraction and recognition algorithm was researched and analyzed. Through the simulation calculation and experimental verification, the results show that target characteristics model and recognition algorithm is feasible.

영상 안정화를 이용한 고속화된 지상 이동 표적 탐지 방법

김정석,김대환 한국정보과학회 2022 정보과학회 컴퓨팅의 실제 논문지 Vol.28 No.7

Moving target indication (MTI) has been widely used as a technology for detecting moving targets. The moving target indication technique can effectively detect a moving target by generating a difference image between the previous and current images. However, a moving target indication technique must be used for each frame, which causes a very large amount of computation from the signal processor. Also, there is a risk of providing inaccurate detection information to the tracking filter due to image stabilization failure. This paper describes image stabilization and moving target candidate detection methods for moving target detection. The frame interval to be used for image stabilization is adjusted using the moving target size or distance information. It is designed to increase the usability of image data through the use of multi-process for image stabilization. It is possible to detect moving target in a short time by increasing the usability of image data. According to the image stabilization success determination logic, moving target detection is performed only when image stabilization is successful. Through this, it is possible to minimize the effect of image stabilization failure and to detect moving target stably. 이동표적을 탐지하는 기술로 이동표적표시 기술(MTI, Moving target indication)이 많이 사용되어왔다. 이동표적표시 기술은 이전, 현재 영상 간의 차영상 생성을 통해 효과적으로 이동물체를 검출할 수 있는 기술이다. 단, 차영상 생성을 위해 영상 안정화 및 영상 전처리, 매 프레임마다 이동표적표시 기술을 사용하여야 하는데 신호처리기 입장에선 매우 부담스러운 연산량을 유발한다. 또한 영상 안정화 실패로 인해 부정확한 검출 정보를 추적 필터에 제공하게 되는 위험성이 존재한다. 본 논문에서는 지상 이동 표적 탐지를 위하여 신뢰도를 보장한 영상 안정화 고속화 방법과 이동표적 후보 탐지 방법에 대하여 설명한다. 영상 내 이동 표적 사이즈 또는 표적과의 거리 정보를 이용하여 영상 안정화에 사용될 프레임 간격을 동적으로 조절하고, 영상 안정화를 위한 멀티 프로세스 운용을 통해 영상 데이터의 활용성을 높일 수 있도록 설계하였다. 영상 데이터의 활용성을 높임으로써, 이동 물체 탐지를 빠른 시간 안에 할 수 있으며, 영상 안정화 성공 판단 로직에 따라 영상 안정화에 성공한 프레임만을 이동 물체 검출에 사용하기 때문에 영상 안정화 실패 시에 미치는 영향성을 최소화하고, 안정적으로 이동 물체를 탐지할 수 있도록 설계하였다.

저피탐 표적 탐지 레이다를 위한 이동 표적 거리 고해상도 처리 기법

손제경(Jegyung Son) 한국정보기술학회 2023 한국정보기술학회논문지 Vol.21 No.5

For detection of low observable target, high power and false target removal capability of radar are required. Since false targets consume limited resources of the radar and hinder the detection of targets of interest, a detection technique that effectively removes them is required. To this end, in this paper, we propose a new method for detecting low observable moving targets. The proposed method removes clutter and non-interest stationary targets and increases the signal-to-clutter ratio of the moving target by combining a simple stationary target removal technique and a high range resolution processing technique. Afterwards, it provides selective target detection function by identifying shape from the high resolution range image of target. To verify the effectiveness of the proposed method, a signal simulating the sea environment is used, and the experimental results prove that the proposed method can effectively detect low observable moving targets.

Systematic Change Detection With Spectral Similarity Measures of SID for Uranium Tailing Piles to Monitor Suspicious Mining Activities in the Pyongsan Uranium Mine

Hoseong Choi,Gayeon Ha,Minsoo Kim 한국방사성폐기물학회 2022 한국방사성폐기물학회 학술논문요약집 Vol.20 No.1

With the enhancement of the spatial resolution of satellite imagery (1 m or less), the satellite image analysis has been considered as the indispensable means for remote sensing of nuclear proliferation activities in the restricted access areas such as North Korea. Notably, in the case of an open-pit uranium mine, e.g. the Pyongsan uranium mine, the mining activity can be presumed if detecting the location and extent uranium tailing piles near shafts within temporal images. Several studies have researched on the target detection for minerals of interest such as limestone and coal to evaluate the economic activities by utilizing similarity measures, e.g., a spectral angle mapper and a spectral information divergence (SID). Thus, this paper presented a systematic change detection methodology for monitoring the uranium mining activity in the Pyongsan uranium mine with a similarity measure of SID. The proposed methodology using the target detection results consists of the following five steps. The first step is to acquire stereo images of areas of interest for change detection. The second step is to preprocess the stereo images as following measures: (i) the QUick Atmospheric Correction and the image-to-image registration with ENVI and (ii) the Gram-Schmidt pansharpening. The third step is to extract spectral information for minerals of interest, i.e., uranium tailing piles, by sampling pixels within the reference image. It is based on the satellite analysis report for the Pyongsan uranium mine by CSIS, which specified the location of the uranium tailing piles. As the fourth step, the target detection for uranium tailing piles was performed through the similarity measure of SID between the extracted spectral information and the spectral reflectance of the image. In the fifth step, the change detection was processed using the multivariate alteration detection algorithm, which compares the target detection results by canonical correlation analysis. Furthermore, this paper evaluated the performance of the proposed methodology with the change detection accuracy assessment index, i.e., the area under a receiver operating characteristic curve. In conclusion, this paper suggests the systematic change detection methodology utilizing time series analysis of target detection for uranium tailing piles, which can save time and cost for humans to interpret large amounts of satellite information at the restricted access areas. As future works, the feasibility of the proposed methodology would be investigated by analyzing distribution of minerals of interest regarding nuclear proliferation at Yongbyon, which has the historical events of suspicious nuclear activities.

Spatio-Temporal Saliency Fusion Based Small Infrared Moving Target Detection Under Sea-Sky Background

Li Shaoyi,Wang Xiaotian,Zhang Kai,Niu Saisai,Zou Yijun 제어로봇시스템학회 2019 제어로봇시스템학회 국제학술대회 논문집 Vol.2019 No.10

Small infrared moving target detection has an important role in the sea-based infrared search and tracking, maritime area surveillance and other applications. This method aims to detect the small infrared moving targets with the sea-sky background. The present study proposes a detection algorithm for small infrared targets based on the spatio-temporal saliency fusion. The contourlet analysis and edge extraction are carried out in the concurrent design. In order to effectively suppress the background and improve the target signal-clutter ratio, the spectral residual method is combined with the abovementioned methods to reconstruct the target fusion saliency image. Then the target motion region is estimated based on the optical flow method for the fusion saliency image and it is matched with the target area of interest to achieve the moving target detection. Moreover, the pipeline filtering is introduced to achieve the target confirmation by multi-frame judgment, reduce false alarm rate and complete the moving target detection for the infrared image sequence. Experimental results show that the proposed algorithm can achieve continuous target detection and have a higher detection precision via real long wave infrared image sequences.

FPGA-Based Real-Time Multi-Scale Infrared Target Detection on Sky Background

Kim, Hun-Ki,Jang, Kyung-Hyun 한국컴퓨터정보학회 2016 韓國컴퓨터情報學會論文誌 Vol.21 No.11

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.

검도선수와 사격선수의 시각탐지차이에 관한 연구

권오영,김남규 한국스포츠심리학회 2004 한국스포츠심리학회지 Vol.15 No.1

본 연구는 시각탐지과제를 사용하여 주의집중의 유형이 다른 검도선수와 사격선수가 표적자극을 탐지하는데 영향을 미치는 요인을 밝혀보고 시각탐지의 차이를 알아보고자 수행되었다. 실험 모두 시각탐지과제를 사용하였으며, 표적 유형은 배경자극과 방향차원에서 차이나는 방향 표적과 세부특징에서 차이나는 세부특징 표적이었으며, 표적위치는 사사분면으로 구분하였다. 실험 1에서는 표적과 배경자극이 모두 정지되어있는 상황에서의 탐색을 다루었다. 실험 결과, 표적자극에 대한 탐지시간은 표적자극의 유형에 관계없이 사격선수가 검도선수보다 더 빠른 경향성을 보였다. 또한, 방향 표적이 세부특징 표적보다 빨리 탐지되었으며, 제1사분면에 제시된 표적이 가장 빠르게 탐지되는 위치우위성 효과를 보였다. 실험 2에서는 표적과 배경자극이 모두 운동하는 상황에서 표적의 유형과 표적위치가 탐지에 미치는 효과를 다루었다. 자극은 수직방향으로 운동하였다. 그 결과, 사격선수보다 검도선수가 표적유형에 관계없이 더 빨리 표적을 탐지하였다. 위치 우위성효과에서는 실험 1과 약간 차이가 있었다. 제1사분면과 제2사분면에서의 표적탐지가 제3사분면과 제4사분면에서의 표적탐지보다 더 빨랐다. 다가오는 자극에 대한 정체를 빨리 확인하는 것이 멀어져 가는 자극에 대한 정체를 확인하는 것보다 더 생존을 높이기 때문일 수 있다. 또한 검도선수는 세부특징 표적도 빨리 탐지하는 결과를 나타내었다. 이러한 결과는 움직임을 통한 사물지각의 중요성을 나타낸다고 볼 수 있다. This study was to investigate factors that affect the detection of a target in Gun Shooters and Kendo Masters with visual search experimental paradigm, and to compare visual detection difference between them who was different from attention type. The target was different from the background stimuli in either orientation(orientation target) or distinctive feature(feature target), and was presented in one of the four quartile positions in the Cartesian coordinates. In Experiment 1 where both the target and background stimuli were presented statically. The result of the experiment showed that the target tended to be detected faster in Gun Shooters than Kendo Masters. Also it has been discovered that orientation target was detected faster than feature target. Location priority effect was also found. That is, the targets in the first quartile position were detected faster than those in any other positions. Experiment 2 explored the effect of the target types and locations while both the target and the background stimuli were moving in vertical directions. The results showed that the target was detected faster in Kendo Masters than Gun Shooters. And the location priority effect was also found, but the effect was different in Experiment 1. That is, the targets in the first and the second quartile position were detected faster than those in any other positions. Also it has been discovered that feature target was detected as faster as orientation target in Kendo Masters. This result showed the importance of perception by the movement.

검도선수와 사격선수의 시각탐지차이에 관한 연구

권오형,김남규 한국스포츠심리학회 2004 한국스포츠심리학회지 Vol.15 No.1

This study was to investigate factors that affect the detection of a target in Gun Shooters and Kendo Masters with visual search experimental paradigm, and to compare visual detection difference between them who was different from attention type. The target was different from the background stimuli in either orientation(orientation target) or distinctive feature(feature target), and was presented in one of the four quartile positions in the Cartesian coordinates. In Experiment 1 where both the target and background stimuli were presented statically. The result of the experiment showed that the target tended to be detected faster in Gun Shooters than Kendo Masters. Also it has been discovered that orientation target was detected faster than feature target. Location priority effect was also found. That is, the targets in the first quartile position were detected faster than those in any other positions. Experiment 2 explored the effect of the target types and locations while both the target and the background stimuli were moving in vertical directions. The results showed that the target was detected faster in Kendo Masters than Gun Shooters. And the location priority effect was also found, but the effect was different in Experiment 1. That is, the targets in the first and the second quartile position were detected faster than those in any other positions. Also it has been discovered that feature target was detected as faster as orientation target in Kendo Masters. This result showed the importance of perception by the movement

A Fast Algorithm for Target Detection in High Spatial Resolution Imagery

Kwang Eun Kim 大韓遠隔探査學會 2006 大韓遠隔探査學會誌 Vol.22 No.1

Detection and identification of targets from remotely sensed imagery are of great interest for civilian and military application. This paper presents an algorithm for target detection in high spatial resolution imagery based on the spectral and the dimensional characteristics of the reference target. In this algorithm, the spectral and the dimensional information of the reference target is extracted automatically from the sample image of the reference target. Then in the entire image, the candidate target pixels are extracted based on the spectral characteristics of the reference target. Finally, groups of candidate pixels which form isolated spatial objects of similar size to that of the reference target are extracted as detected targets. The experimental test results showed that even though the algorithm detected spatial objects which has different shape as targets if the spectral and the dimensional characteristics are similar to that of the reference target, it could detect 97.5% of the targets in the image. Using hyperspectral image and utilizing the shape information are expected to increase the performance of the proposed algorithm.