Wearable visual robots

Mayol, W.W.; Tordoff, B.J.; Murray, David

doi:10.1109/iswc.2000.888470

Cited by 43 publications

(20 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This consists of a camera mounted on the shoulder; an inertial measurement unit (IMU), which assists in stabilizing the camera and allowing it to make fast redirections of gaze when motion blurs visual feedback; a hand-held touch screen display with a camera mounted on the rear; and a portable computer carried in a shoulder bag. The active camera is broadly similar to that built earlier in this laboratory by Mayol [36], but differs in the detail of the control electronics and mounting, and in overall refinement.…”

Section: Methodsmentioning

confidence: 99%

Combining monoSLAM with object recognition for scene augmentation using a wearable camera

Castle

Klein

Murray

2010

Image and Vision Computing

Self Cite

View full text Add to dashboard Cite

Section: Methodsmentioning

confidence: 99%

Combining monoSLAM with object recognition for scene augmentation using a wearable camera

Castle

Klein

Murray

2010

Image and Vision Computing

Self Cite

View full text Add to dashboard Cite

“…Egocentric vision has been extensively studied [19,28,21,5,15,6] in many contexts such as face recognition, gesture recognition, visual SLAM or virtual reality. Object recognition from a wearable camera typically detects ambient or static objects in the environment [27,20].…”

Section: Introductionmentioning

confidence: 99%

Egocentric recognition of handled objects: Benchmark and analysis

Ren

Philipose

2009

2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops

View full text Add to dashboard Cite

Recognizing objects being manipulated in hands can provide essential information about a person's activities and have far-reaching impacts on the application of visionin everyday life. The egocentric viewpoint from a wearable camera has unique advantages in recognizing handled objects, such as having a close view and seeing objects in their natural positions. We collect a comprehensive dataset and analyze the feasibilities and challenges of the egocentric recognition of handled objects.We use a lapel-worn camera and record uncompressed video streams as human subjects manipulate objects in daily activities. We use 42 day-to-day objects that vary in size, shape, color and textureness. 10 video sequences are shot for each object under different illuminations and backgrounds. We use this dataset and a SIFT-based recognition system to analyze and quantitatively characterize the main challenges in egocentric object recognition, such as motion blur and hand occlusion, along with its unique constraints, such as hand color, location prior and temporal consistency. SIFT-based recognition has an average recognition rate of 12%, and reaches 20% through enforcing temporal consistency. We use simulations to estimate the upper bound for SIFT-based recognition at 64%, the loss of accuracy due to background clutter at 20%, and that of hand occlusion at 13%. Our quantitative evaluations show that the egocentric recognition of handled objects is a challenging but feasible problem with many unique characteristics and many opportunities for future research.

show abstract

“…So the decision has been made to use the Helmholtz chain "tilt then pan" to achieve a flat construction. This configuration leads to cyclotorsional motions around the optical axis of the camera (roll axis, [9]). However, for small motions around pan and tilt axis, the described disadvantage of cyclotorsion is not critical.…”

Section: General System Descriptionmentioning

confidence: 99%

A Motion Device for a Stabilized Vehicle Camera System with Control Parameter Optimization

Wagner

Günthner

Ulbrich

2006

2006 IEEE International Symposium on Industrial Electronics

View full text Add to dashboard Cite

Stable image processing often needs movable camera systems. Either the camera has to be steered into desired gaze directions, for example during the tracking of objects, or an inertially stabilized camera image is needed as a basis for robust image processing algorithms. In many applications combinations of both situations are possible. In this work the design and implementation of a camera motion device that serves as an experimental platform for laboratory purposes as well as a prototype of a stabilized vehicle camera is presented. In the vehicle application, the inertial stabilized camera is the basis for different driving assistance systems based on robust optical scene interpretation. For the inertial stabilization of the camera, the human gaze stabilization system has been used as a pattern. An approach to an optimal regulation tuning for the device in the given application during typical operation is described. The results of the optimization are presented. The optimized system has been validated during test drives.

show abstract

Wearable visual robots

Cited by 43 publications

References 22 publications

Combining monoSLAM with object recognition for scene augmentation using a wearable camera

Combining monoSLAM with object recognition for scene augmentation using a wearable camera

Egocentric recognition of handled objects: Benchmark and analysis

A Motion Device for a Stabilized Vehicle Camera System with Control Parameter Optimization

Contact Info

Product

Resources

About