• Journal of Korea Multimedia Society
• /
• v.24 no.5
• /
• pp.659-666
• /
• 2021

With the continuous development of deep learning, human behavior recognition algorithms have achieved good results. However, in a multi-person recognition environment, the complex behavior environment poses a great challenge to the efficiency of recognition. To this end, this paper proposes a multi-person pose estimation model. First of all, the human detectors in the top-down framework mostly use the two-stage target detection model, which runs slow down. The single-stage YOLOv3 target detection model is used to effectively improve the running speed and the generalization of the model. Depth separable convolution, which further improves the speed of target detection and improves the model's ability to extract target proposed regions; Secondly, based on the feature pyramid network combined with context semantic information in the pose estimation model, the OHEM algorithm is used to solve difficult key point detection problems, and the accuracy of multi-person pose estimation is improved; Finally, the Euclidean distance is used to calculate the spatial distance between key points, to determine the similarity of postures in the frame, and to eliminate redundant postures.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.17 no.4
• /
• pp.422-429
• /
• 2014

Proximity sensor networks are aimed at estimation kinematic state of target using estimated position of the target by each sensor node or target parameter. To analyze the kinematic state of target, traditional approaches require detections on multiple sensors, very large number of sensors to achieve acceptable performance. In this paper, we propose a novel method which can estimate predicted position of the underwater target using minimum proximity sensor with bearing information to this problem. The proposed algorithm was verified performance through simulation.

• Journal of Institute of Control, Robotics and Systems
• /
• v.17 no.8
• /
• pp.783-789
• /
• 2011

Target tracking performance improvement using multi-sensor data fusion is a challenging work. However, biases in the measurements should be removed before various data fusion techniques are applied. In this paper, a bias removing algorithm using measurement data from multi-radar tracking systems is proposed and evaluated by computer simulation. To predict bias estimation performance in various geometric relations between the radar systems and target, a system observability index is proposed and tested via computer simulation results. It is also studied that target tracking which utilizes multi-sensor data fusion with bias-removed measurements results in better performance.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.27 no.6
• /
• pp.539-544
• /
• 2016

This paper improves Sherman's two-pulse method for angle estimation of two unresolved targets in phase comparison monopulse radar. The proposed method provides the angle information with only a single-pulse measurement instead of two pulses. The proposed method can estimate a single-target angle by single-target indicator, in contrast with previous techniques. The accuracy of angle estimation for proposed method is demonstrated by simulations.

• Journal of Institute of Control, Robotics and Systems
• /
• v.21 no.2
• /
• pp.162-167
• /
• 2015

In this paper, we propose a F-MBE algorithm for Dual mode seeker (CCD and IIR). The MBE algorithm show improved performance at the IIR target size estimation. but the MBE can't use at Dual Mode seeker. To overcome this problem,, we apply template matching method for CCD target size information. The performance of proposed F-MBE method is tested at target intercept scenario of dual mode seeker equipped missile. The experiment results show that the proposed algorithm has the relatively improved performance.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09b
• /
• pp.99-102
• /
• 2003

A new interacting multiple model (IMM) method using genetic algorithm (GA)-based intelligent input estimation(IIE) is proposed to track a maneuvering target. In the proposed method, the acceleration level for each sub-model is determined by IIE-the estimation of the unknown acceleration input by a fuzzy system using the relation between maneuvering filter residual and non-maneuvering one. The GA is utilized to optimize a fuzzy system fur a sub-model within a fixed range of acceleration input. Then, multiple models are composed of these fuzzy systems, which are optimized for different ranges of acceleration input. In computer simulation for an incoming ballistic missile, the tracking performance of the proposed method is compared with those of the input estimation(IE) technique and the adaptive interacting multiple model (AIMM) method.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.14 no.6
• /
• pp.1198-1206
• /
• 2011

In this paper, a sensor bias estimation method with pseudo measurement for asynchronous multisensor systems is proposed. The proposed bias estimation method separates the local filter which estimates the target state with biased measurements into two parts, one is bias part, the other is target state part. By using these two parts, the algorithm generates the pseudo bias measurement for estimating bias, and then eliminates bias of local track through bias compensation. Finally, the proposed algorithm is evaluated by comparing with the existing EXX method.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.53 no.2
• /
• pp.133-140
• /
• 2016

In active sonar field, a target detection and localization based on a distributed sensor network has been much studied for the underwater surveillance of the coast. Zhou et al. proposed a target localization method utilizing the positions of target-detected sensors in distributed sensor network which consists of detection-only sensors. In contrast with a conventional method, Zhou's method dose not require to estimate the propagation model parameters of detection signal. Also it needs the lower computational complexity, and to transmit less data between network nodes. However, it has large target localization error. So it has been modified for reducing localization error by Ryu. Modified Zhou's method has better estimation performance than Zhou's method, but still relatively large estimation error. In this paper, a target localization method based on modified Zhou's method is proposed for reducing the localization error. The proposed method utilizes the geometry of the positions of target-detected sensors and a line that represents the bearing of target, a line can be found by modified Zhou's method. This paper shows that the proposed method has better target position estimation performance than Zhou's and modified Zhou's method by computer simulations.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.11
• /
• pp.5624-5638
• /
• 2016

A novel method based on Surf points is proposed to detect and lock-track single ground target in aerial videos. Videos captured by moving cameras contain complex motions, which bring difficulty in moving object detection. Our approach contains three parts: moving target template detection, search area estimation and target tracking. Global motion estimation and compensation are first made by grids-sampling Surf points selecting and matching. And then, the single ground target is detected by joint spatial-temporal information processing. The temporal process is made by calculating difference between compensated reference and current image and the spatial process is implementing morphological operations and adaptive binarization. The second part improves KALMAN filter with surf points scale information to predict target position and search area adaptively. Lastly, the local Surf points of target template are matched in this search region to realize target tracking. The long-term tracking is updated following target scaling, occlusion and large deformation. Experimental results show that the algorithm can correctly detect small moving target in dynamic scenes with complex motions. It is robust to vehicle dithering and target scale changing, rotation, especially partial occlusion or temporal complete occlusion. Comparing with traditional algorithms, our method enables real time operation, processing $520{\times}390$ frames at around 15fps.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.64 no.3
• /
• pp.445-450
• /
• 2015

In the moving target problem, the velocity information of the moving target is very important as well as the high accuracy position information. To solve this problem, active researches are being conducted recently with combine the Time Difference of Arrival (TDOA) and Frequency Delay of Arrival(FDOA) measurements. However, since the FDOA measurement is utilizing the Doppler effect due to the relative velocity between the target source and the receiver sensor, it may be difficult to use the FDOA measurement if the moving target speed is not sufficiently fast. In this paper, we propose a method for estimating the position and the velocities of the target by using only the TDOA measurements for the low speed moving target in the indoor environment with sensor network. First, the target position and heading angle are obtained from the estimated positions of two attached transmitters on the target. Then, the target angular and linear velocities are also estimated. In addtion, we apply the Instrumental Variable (IV) technique to compensate the estimation error of the estimated target velocity. In simulation, the performance of the proposed algorithm is verified.