Abstract
The latency of a perception system is crucial for a robot performing interactive tasks in dynamic human environments. We present MOPED, a fast and scalable perception system for object recognition and pose estimation. MOPED builds on POSESEQ, a state of the art object recognition algorithm, demonstrating a massive improvement in scalability and latency without sacrificing robustness. We achieve this with both algorithmic and architecture improvements, with a novel feature matching algorithm, a hybrid GPU/CPU architecture that exploits parallelism at all levels, and an optimized resource scheduler. Using the same standard hardware, we achieve up to 30× improvement on real-world scenes.
Keywords
Computer scienceScalabilityRobustness (evolution)Latency (audio)Artificial intelligencePoseCognitive neuroscience of visual object recognitionComputer visionExploitLow latency (capital markets)Feature extractionReal-time computing
Affiliated Institutions
Related Publications
Wide-area cooperative storage with CFS
The Cooperative File System (CFS) is a new peer-to-peer read-only storage system that provides provable guarantees for the efficiency, robustness, and load-balance of file stora...
A scalable content-addressable network
Hash tables - which map "keys" onto "values" - are an essential building block in modern software systems. We believe a similar functionality would be equally valuable to large ...
EfficientDet: Scalable and Efficient Object Detection
Model efficiency has become increasingly important in computer vision. In this paper, we systematically study neural network architecture design choices for object detection and...
VINS-Mono: A Robust and Versatile Monocular Visual-Inertial State Estimator
One camera and one low-cost inertial measurement unit (IMU) form a monocular visual-inertial system (VINS), which is the minimum sensor suite (in size, weight, and power) for th...
Deep High-Resolution Representation Learning for Visual Recognition
High-resolution representations are essential for position-sensitive vision problems, such as human pose estimation, semantic segmentation, and object detection. Existing state-...
Publication Info
- Year
- 2010
- Type
- article
- Citations
- 100
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
100
OpenAlex
Cite This
Manuel Martínez,
Alvaro Collet,
Siddhartha S Srinivasa
(2010).
MOPED: A scalable and low latency object recognition and pose estimation system.
.
https://doi.org/10.1109/robot.2010.5509801
Identifiers
- DOI
- 10.1109/robot.2010.5509801