• International Journal of Aeronautical and Space Sciences
• /
• v.12 no.3
• /
• pp.252-259
• /
• 2011

This paper is focused on dynamic modeling and control system design as well as vision based collision avoidance for multi-rotor unmanned aerial vehicles (UAVs). Multi-rotor UAVs are defined as rotary-winged UAVs with multiple rotors. These multi-rotor UAVs can be utilized in various military situations such as surveillance and reconnaissance. They can also be used for obtaining visual information from steep terrains or disaster sites. In this paper, a quad-rotor model is introduced as well as its control system, which is designed based on a proportional-integral-derivative controller and vision-based collision avoidance control system. Additionally, in order for a UAV to navigate safely in areas such as buildings and offices with a number of obstacles, there must be a collision avoidance algorithm installed in the UAV's hardware, which should include the detection of obstacles, avoidance maneuvering, etc. In this paper, the optical flow method, one of the vision-based collision avoidance techniques, is introduced, and multi-rotor UAV's collision avoidance simulations are described in various virtual environments in order to demonstrate its avoidance performance.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.67 no.9
• /
• pp.1224-1231
• /
• 2018

Automatic age estimation has been used in many social network applications, practical commercial applications, and human-computer interaction visual-surveillance biometrics. However, it has rarely been explored. In this paper, we propose an automatic age estimation system, which includes face detection and convolutional deep learning based on an inception module. The latter is a 22-layer-deep network that serves as the particular category of the inception design. To evaluate the proposed approach, we use 4,000 images of eight different age groups from the Adience age dataset. k-fold cross-validation (k = 5) is applied. A comparison of the performance of the proposed work and recent related methods is presented. The results show that the proposed method significantly outperforms existing methods in terms of the exact accuracy and off-by-one accuracy. The off-by-one accuracy is when the result is off by one adjacent age label to the above or below. For the exact accuracy, the age label of "60+" is classified with the highest accuracy of 76%.

• Journal of Information Processing Systems
• /
• v.13 no.5
• /
• pp.1299-1319
• /
• 2017

This paper presents a scalable multiple camera collaboration strategy for active tracking applications in large areas. The proposed approach is based on distributed mechanism but emulates the master-slave mechanism. The master and slave cameras are not designated but adaptively determined depending on the object dynamic and density distribution. Moreover, the number of cameras emulating the master is not fixed. The collaboration among the cameras utilizes global and local sectors in which the visual correspondences among different cameras are determined. The proposed method combines the local information to construct the global information for emulating the master-slave operations. Based on the global information, the load balancing of active tracking operations is performed to maximize active tracking coverage of the highly dynamic objects. The dynamics of all objects visible in the local camera views are estimated for effective coverage scheduling of the cameras. The active tracking synchronization timing information is chosen to maximize the overall monitoring time for general surveillance operations while minimizing the active tracking miss. The real-time simulation result demonstrates the effectiveness of the proposed method.

• Smart Media Journal
• /
• v.11 no.8
• /
• pp.84-92
• /
• 2022

Precision livestock monitoring promises greater management efficiency for farmers and higher welfare standards for animals. Recent studies on video-based animal activity recognition and tracking have shown promising solutions for understanding animal behavior. To achieve that, surveillance cameras are installed diagonally above the barn in a typical cattle farm setup to monitor animals constantly. Under these circumstances, tracking individuals requires addressing challenges such as occlusion and visual appearance, which are the main reasons for track breakage and increased misidentification of animals. This paper presents a framework for multi-cattle tracking in closed barns with appearance and motion models. To overcome the above challenges, we modify the DeepSORT algorithm to achieve higher tracking accuracy by three contributions. First, we reduce the weight of appearance information. Second, we use an Ensemble Kalman Filter to predict the random motion information of cattle. Third, we propose a supplementary matching algorithm that compares the absolute cattle position in the barn to reassign lost tracks. The main idea of the matching algorithm assumes that the number of cattle is fixed in the barn, so the edge of the barn is where new trajectories are most likely to emerge. Experimental results are performed on our dataset collected on two cattle farms. Our algorithm achieves 70.37%, 77.39%, and 81.74% performance on HOTA, AssA, and IDF1, representing an improvement of 1.53%, 4.17%, and 0.96%, respectively, compared to the original method.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.22
• /
• pp.9731-9737
• /
• 2014

Large scale secular registry or surveillance systems have been accumulating vast data that allow mathematical modeling of cancer incidence and mortality rates. Most contemporary models in this regard use time series and APC (age-period-cohort) methods and focus primarily on predicting or analyzing cancer epidemiology with little attention being paid to implications for designing cancer registry, surveillance or evaluation initiatives. This research models age-specific cancer incidence rates using logistic growth equations and explores their performance under different scenarios of data completeness in the hope of deriving clues for reshaping relevant data collection. The study used China Cancer Registry Report 2012 as the data source. It employed 3-parameter logistic growth equations and modeled the age-specific incidence rates of all and the top 10 cancers presented in the registry report. The study performed 3 types of modeling, namely full age-span by fitting, multiple 5-year-segment fitting and single-segment fitting. Measurement of model performance adopted adjusted goodness of fit that combines sum of squred residuals and relative errors. Both model simulation and performance evalation utilized self-developed algorithms programed using C# languade and MS Visual Studio 2008. For models built upon full age-span data, predicted age-specific cancer incidence rates fitted very well with observed values for most (except cervical and breast) cancers with estimated goodness of fit (Rs) being over 0.96. When a given cancer is concerned, the R valuae of the logistic growth model derived using observed data from urban residents was greater than or at least equal to that of the same model built on data from rural people. For models based on multiple-5-year-segment data, the Rs remained fairly high (over 0.89) until 3-fourths of the data segments were excluded. For models using a fixed length single-segment of observed data, the older the age covered by the corresponding data segment, the higher the resulting Rs. Logistic growth models describe age-specific incidence rates perfectly for most cancers and may be used to inform data collection for purposes of monitoring and analyzing cancer epidemic. Helped by appropriate logistic growth equations, the work vomume of contemporary data collection, e.g., cancer registry and surveilance systems, may be reduced substantially.

• Journal of Korea Multimedia Society
• /
• v.11 no.3
• /
• pp.301-314
• /
• 2008

The existing event recognition is accomplished with the limited systematic foundation, and thus much longer learning time is needed for emergency scenario interpretation due to large scale of probability data. In this paper, we propose a method for nile-based event recognition of an independent object(human) which extract a feature vectors from the object and analyze the behavior pattern of each object and interpretation of emergency scenarios using a probability and object's events. The event rule of an independent object is composed of the Primary-event, Move-event, Interaction-event, and 'FALL DOWN' event and is defined through feature vectors of the object and the segmented motion orientated vector (SMOV) in which the dynamic Bayesian network is applied. The emergency scenario is analyzed using current state of an event and its post probability. In this paper, we define diversified events compared to that of pre-existing method and thus make it easy to expand by increasing independence of each events. Accordingly, semantics information, which is impossible to be gained through an.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.3
• /
• pp.2117-2122
• /
• 2015

Wide FOV(Field-of-View) is required to contain much more visual information in a single image. The wide FOV imaging system has many industrial applications such as surveillance, security, tele-conference, and mobile robots. In order to obtain a wide FOV panorama image, an imaging system with hyperbolic cylinder mirror is proposed in this paper. Because the horizontal FOV is more important than the vertical FOV in general, a hyperbolic cylinder mirror is designed in this paper, that has a hyperbolic curve in the horizontal surface and is the same as a planar mirror in the vertical axis. Imaging model of the proposed imaging system is presented by ray tracing method and the hyperbolic cylinder mirror is implemented. The imaging performance of wide FOV is verified by experiments in this paper. This imaging system is cost-effective and is possible to acquire a wide panorama image having 210 degree horizontal FOV in real-time without an extra image processing.

• Korean Journal of Veterinary Service
• /
• v.40 no.1
• /
• pp.15-20
• /
• 2017

A two-tube reverse transcription loop-mediated isothermal amplification (RT-LAMP) assay was designed for the rapid visual detection of the M gene of all subtypes of avian influenza virus (AIV) and the H5 gene of the H5 subtype of highly pathogenic AIV (HPAIV). The reaction carried out in two tubes in a single step at $58^{\circ}C$ for 40 min, and the assay results could be visually detected by using hydroxynaphthol blue dye. Using M or H5 gene-specific primers, the assay successfully detected all subtypes or H5 subtypes of AIVs, including the Korean representative H5N1 and H5N8 HPAIVs. The detection limit of the assay was approximately $10^{2.0}$ $EID_{50}/reaction$ for the M and H5 genes of H5N1 HPAIV, respectively, and was more sensitive than that of previously reported RT-LAMP and comparable to that of real-time RT-PCR. These results suggest that the present RT-LAMP assay, with its high specificity, sensitivity, and simplicity, will be a useful diagnostic tool for surveillance of currently circulating H5 HPAIVs and other subtypes of AIV in bird population, even in under-equipped laboratories.

• Journal of Institute of Control, Robotics and Systems
• /
• v.14 no.8
• /
• pp.848-855
• /
• 2008

In this paper, we describe correspondence among multiple images taken by multiple cameras. The correspondence among multiple views is an interesting problem which often appears in the application like visual surveillance or gesture recognition system. We use the principal axis and the ground plane homography to estimate foot of human. The principal axis belongs to the subtracted silhouette-based region of human using subtraction of the predetermined multiple background models with current image which includes moving person. For the calculation of the ground plane homography, we use landmarks on the ground plane in 3D space. Thus the ground plane homography means the relation of two common points in different views. In the normal human being, the foot of human has an exactly same position in the 3D space and we represent it to the intersection in this paper. The intersection occurs when the principal axis in an image crosses to the transformed ground plane from other image. However the positions of the intersection are different depend on camera views. Therefore we construct the correspondence that means the relationship between the intersection in current image and the transformed intersection from other image by homography. Those correspondences should confirm within a short distance measuring in the top viewed plane. Thus, we track a person by these corresponding points on the ground plane. Experimental result shows the accuracy of the proposed algorithm has almost 90% of detecting person for tracking based on correspondence of intersections.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.48 no.5
• /
• pp.45-51
• /
• 2011

In this paper, we propose an unsupervised learning method for modeling motion trajectory patterns effectively. In our approach, observations of an object on a trajectory are treated as words in a document for latent dirichlet allocation algorithm which is used for clustering words on the topic in natural language process. This allows clustering topics (e.g. go straight, turn left, turn right) effectively in complex scenes, such as crossroads. After this procedure, we learn patterns of word sequences in each cluster using Baum-Welch algorithm used to find the unknown parameters in a hidden markov model. Evaluation of abnormality can be done using forward algorithm by comparing learned sequence and input sequence. Results of experiments show that modeling of semantic region is robust against noise in various scene.