Practical 3-D object detection using category and instance-level appearance models

Saenko,; Karayev,; Jia, Jia; Shyr,; Janoch,; Long, Mark D.; Fritz,; Darrell,

doi:10.1109/iros.2011.6048691

Cited by 7 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While the depth cue can be more descriptive, researchers have typically found that the combination of depth with other cues provides the most discrimination in object detection. For example, depth with texture and color from the Kinect RGB camera [Lee et al 2011], depth and color [Stückler and Behnke 2010], local features with histogram of gradients and depth for 3D size constraints [Saenko et al 2011], and size, 3D shape, and depth edges combined into a single local-feature descriptor [Bo et al 2011].…”

Section: Object Detection and Trackingmentioning

confidence: 99%

Cooperative augmentation of mobile smart objects with projected displays

Molyneaux

Gellersen

Finney

2013

ACM Trans. Interact. Intell. Syst.

View full text Add to dashboard Cite

Sensors, processors, and radios can be integrated invisibly into objects to make them smart and sensitive to user interaction, but feedback is often limited to beeps, blinks, or buzzes. We propose to redress this input-output imbalance by augmentation of smart objects with projected displays, that-unlike physical displays-allow seamless integration with the natural appearance of an object. In this article, we investigate how, in a ubiquitous computing world, smart objects can acquire and control a projection. We consider that projectors and cameras are ubiquitous in the environment, and we develop a novel conception and system that enables smart objects to spontaneously associate with projector-camera systems for cooperative augmentation. Projector-camera systems are conceived as generic, supporting standard computer vision methods for different appearance cues, and smart objects provide a model of their appearance for method selection at runtime, as well as sensor observations to constrain the visual detection process. Cooperative detection results in accurate location and pose of the object, which is then tracked for visual augmentation in response to display requests by the smart object. In this article, we define the conceptual framework underlying our approach; report on computer vision experiments that give original insight into natural appearance-based detection of everyday objects; show how object sensing can be used to increase speed and robustness of visual detection; describe and evaluate a fully implemented system; and describe two smart object applications to illustrate the system's cooperative augmentation process and the embodied interactions it enables with smart objects. ACM Reference Format:Molyneaux, D., Gellersen, H., and Finney, J. 2013. Cooperative augmentation of mobile smart objects with projected displays.

show abstract

Section: Object Detection and Trackingmentioning

confidence: 99%

Cooperative augmentation of mobile smart objects with projected displays

Molyneaux

Gellersen

Finney

2013

ACM Trans. Interact. Intell. Syst.

View full text Add to dashboard Cite

show abstract

“…Segmenting a desirable object from background clutter can be done with laser range data [2], colour and texture patterns [8] and depth images [9]. Hard coded segmentation algorithms have difficulty when conditions change and require tuning to the application.…”

Section: Related Workmentioning

confidence: 99%

Robots move: Bootstrapping the development of object representations using sensorimotor coordination

Glover

Wyeth

2012

2012 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

This paper is concerned with the unsupervised learning of object representations by fusing visual and motor information. The problem is posed for a mobile robot that develops its representations as it incrementally gathers data. The scenario is problematic as the robot only has limited information at each time step with which it must generate and update its representations. Object representations are refined as multiple instances of sensory data are presented; however, it is uncertain whether two data instances are synonymous with the same object. This process can easily diverge from stability. The premise of the presented work is that a robot's motor information instigates successful generation of visual representations. An understanding of self-motion enables a prediction to be made before performing an action, resulting in a stronger belief of data association. The system is implemented as a data-driven partially observable semi-Markov decision process. Object representations are formed as the process's hidden states and are coordinated with motor commands through state transitions. Experiments show the prediction process is essential in enabling the unsupervised learning method to converge to a solution -improving precision and recall over using sensory data alone.

show abstract