Recognition from Hand Cameras
نویسندگان
چکیده
We propose HandCam (Fig. 1), a novel wearable camera capturing activities of hands, for recognizing human behaviors. HandCam has two main advantages over egocentric systems [10, 5, 23]: (1) it avoids the need to detect hands and manipulation regions; (2) it observes the activities of hands almost at all time. These nice properties enable HandCam to recognize hand states (free v.s. active hands, hand gestures, object categories), and discover object categories through interaction with hands. We propose a new method to accomplish these tasks by fusing per-frame state prediction with state changes estimation from a pair of frames. We have collected one of the first HandCam dataset with 20 videos captured in three scenes. Experiments show that HandCam system significantly outperforms a state-ofthe-art HeadCam system (frame-based re-implementation similar to [17]) in all tasks by at most 10.8% improvement in accuracy. We also show that HandCam videos captured by different users can be easily aligned to improve free v.s. active recognition accuracy (3.3% improvement) in crossscenes use case. Moreover, we observe that finetuning Convolutional Neural Network [14] consistently improves accuracy (at most 4.9% better). Finally, a method combining HandCam and HeadCam features achieves the best performance. With more data, we believe a joint HandCam and HeadCam system can robustly log hand states in daily life.
منابع مشابه
Three-Dimensional Hand Pointing Recognition Using Two Cameras by Interpolation and Integration of Classification Scores
In this paper, we propose a novel method of hand recognition for remote mid-air pointing operation. In the proposed method, classification scores are calculated in a sliding window for hand postures with different pointing directions. Detection of a pointing hand and estimation of the pointing direction is performed by interpolating the classification scores. Moreover, we introduce two cameras ...
متن کاملApproach to Hand Tracking and Gesture Recognition Based on Depth-Sensing Cameras and EMG Monitoring
In this paper, a new approach for hand tracking and gesture recognition based on the Leap Motion device and surface electromyography (SEMG) is presented. The system is about to process the depth image information and the electrical activity produced by skeletal muscles on forearm. The purpose of such combination is enhancement in the gesture recognition rate. As a first we analyse the conventio...
متن کاملRobust Sign Language Recognition System Using ToF Depth Cameras
Sign language recognition is a difficult task, yet required for many applications in real-time speed. Using RGB cameras for recognition of sign languages is not very successful in practical situations and accurate 3D imaging requires expensive and complex instruments. With introduction of Time-of-Flight (ToF) depth cameras in recent years, it has become easier to scan the environment for accura...
متن کاملA Hand Gesture Recognition Library for a 3D Viewer Supported by Kinect’s Depth Sensor
In modern life, human–computer interaction has received the most interest from researchers, especially in developing new interaction methods. Microsoft’s Kinect sensor, which has integrated red-green-blue and depth (RGB+D) cameras, opens up new possibilities As well, many three-dimensional (3D) applications have been developed fashioning the computer world more natural and real for the user. In...
متن کاملGesture Recognition Technique:A Review
Gesture Recognition means identification and recognition of gestures originated from any type of bodily motion commonly originated from face or hand. It is a technology with the goal of interpreting human gestures via mathematical algorithms; also referred as perceptual user interface (PUI). Gesture recognition enables humans to interact with the machine (HMI) naturally without any physical con...
متن کاملFeature descriptors for depth-based hand gesture recognition
Depth data acquired by consumer depth cameras provide a very informative description of the hand pose that can be exploited for accurate gesture recognition. A typical hand gesture recognition pipeline requires to identify the hand, extract some relevant features and exploit a suitable machine learning technique to recognize the performed gesture. This chapter deals with the recognition of stat...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- CoRR
دوره abs/1512.01881 شماره
صفحات -
تاریخ انتشار 2015