Continuous human action recognition using depth-MHI-HOG and a spotter model.

In this paper, we propose a new method for spotting and recognizing continuous human actions using a vision sensor. The method is comprised of depth-MHI-HOG (DMH), action modeling, action spotting, and recognition. First, to effectively separate the foreground from background, we propose a method called DMH. It includes a standard structure for segmenting images and extracting features by using depth information, MHI, and HOG. Second, action modeling is performed to model various actions using extracted features. The modeling of actions is performed by creating sequences of actions through k-means clustering; these sequences constitute HMM input. Third, a method of action spotting is proposed to filter meaningless actions from continuous actions and to identify precise start and end points of actions. By employing the spotter model, the proposed method improves action recognition performance. Finally, the proposed method recognizes actions based on start and end points. We evaluate recognition performance by employing the proposed method to obtain and compare probabilities by applying input sequences in action models and the spotter model. Through various experiments, we demonstrate that the proposed method is efficient for recognizing continuous human actions in real environments.

Best basis selection method using learning weights for face recognition.

In the face recognition field, principal component analysis is essential to the reduction of the image dimension. In spite of frequent use of this analysis, it is commonly believed that the basis faces with large eigenvalues are chosen as the best subset in the nearest neighbor classifiers. We propose an alternative that can predict the classification error during the training steps and find the useful basis faces for the similarity metrics of the classical pattern algorithms. In addition, we also show the need for the eye-aligned dataset to have the pure face. The experiments using face images verify that our method reduces the negative effect on the misaligned face images and decreases the weights of the useful basis faces in order to improve the classification accuracy.

A vision-based automated guided vehicle system with marker recognition for indoor use.

We propose an intelligent vision-based Automated Guided Vehicle (AGV) system using fiduciary markers. In this paper, we explore a low-cost, efficient vehicle guiding method using a consumer grade web camera and fiduciary markers. In the proposed method, the system uses fiduciary markers with a capital letter or triangle indicating direction in it. The markers are very easy to produce, manipulate, and maintain. The marker information is used to guide a vehicle. We use hue and saturation values in the image to extract marker candidates. When the known size fiduciary marker is detected by using a bird's eye view and Hough transform, the positional relation between the marker and the vehicle can be calculated. To recognize the character in the marker, a distance transform is used. The probability of feature matching was calculated by using a distance transform, and a feature having high probability is selected as a captured marker. Four directional signals and 10 alphabet features are defined and used as markers. A 98.87% recognition rate was achieved in the testing phase. The experimental results with the fiduciary marker show that the proposed method is a solution for an indoor AGV system.

Intelligent emergency stop algorithm for a manipulator using a new regression method.

In working environments with large manipulators, accidental collisions can cause severe personal injuries and can seriously damage manipulators, necessitating the development of an emergency stop algorithm to prevent such occurrences. In this paper, we propose an emergency stop system for the efficient and safe operation of a manipulator by applying an intelligent emergency stop algorithm. Our proposed intelligent algorithm considers the direction of motion of the manipulator. In addition, using a new regression method, the algorithm includes a decision step that determines whether a detected object is a collision-causing obstacle or a part of the manipulator. We apply our emergency stop system to a two-link manipulator and assess the performance of our intelligent emergency stop algorithm as compared with other models.

Evaluation of a bio-impedance method for measuring human arm movement.

This study proposes a new method for measuring upper limb movement using a bio-impedance technique. Bio-impedance and joint angle were simultaneously measured during the wrist and elbow movements of 12 normal subjects. The joint angles of the wrist and elbow were estimated by measuring the bio-impedances of the forearm and upper arm, respectively. Although the measured bio-impedances on upper limbs varied among individuals, changes in the bio-impedances and joint angles of the wrist and elbow during their extension and flexion were very highly correlated, having correlation coefficients of 0.96 +/- 0.04 and -0.98 +/- 0.02, respectively. The reproducibilities of wrist and elbow bio-impedance changes were 2.1 +/- 1.0% and 1.8 +/- 1.0%, respectively. Since the proposed method is not restricted by size or the duration of measurements, it is expected to be useful for the analysis of athletic movement.

Algorithm for detecting human faces based on convex-hull.

In this paper, we proposed a new method to detect faces in color based on the convex-hull. We detect two kinds of regions that are skin and hair likeness region. After preprocessing, we apply the convex-hull to their regions and can find a face from their intersection relationship. The proposed algorithm can accomplish face detection in an image involving rotated and turned faces as well as several faces. To validity the effectiveness of the proposed method, we make experiment with various cases.