PixRO: Pixel-Distributed Rotational Odometry with Gaussian Belief Propagation
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916912465707008 |
|---|---|
| author | Alzugaray, Ignacio Murai, Riku Davison, Andrew |
| author_facet | Alzugaray, Ignacio Murai, Riku Davison, Andrew |
| contents | Images are the standard input for most computer vision algorithms. However, their processing often reduces to parallelizable operations applied locally and independently to individual pixels. Yet, many of these low-level raw pixel readings only provide redundant or noisy information for specific high-level tasks, leading to inefficiencies in both energy consumption during their transmission off-sensor and computational resources in their subsequent processing.
As novel sensors featuring advanced in-pixel processing capabilities emerge, we envision a paradigm shift toward performing increasingly complex visual processing directly in-pixel, reducing computational overhead downstream. We advocate for synthesizing high-level cues at the pixel level, enabling their off-sensor transmission to directly support downstream tasks more effectively than raw pixel readings.
This paper conceptualizes a novel photometric rotation estimation algorithm to be distributed at pixel level, where each pixel estimates the global motion of the camera by exchanging information with other pixels to achieve global consensus. We employ a probabilistic formulation and leverage Gaussian Belief Propagation (GBP) for decentralized inference using messaging-passing. The proposed proposed technique is evaluated on real-world public datasets and we offer a in-depth analysis of the practicality of applying GBP to distributed rotation estimation at pixel level. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_09726 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | PixRO: Pixel-Distributed Rotational Odometry with Gaussian Belief Propagation Alzugaray, Ignacio Murai, Riku Davison, Andrew Computer Vision and Pattern Recognition Distributed, Parallel, and Cluster Computing Multiagent Systems Robotics Image and Video Processing Images are the standard input for most computer vision algorithms. However, their processing often reduces to parallelizable operations applied locally and independently to individual pixels. Yet, many of these low-level raw pixel readings only provide redundant or noisy information for specific high-level tasks, leading to inefficiencies in both energy consumption during their transmission off-sensor and computational resources in their subsequent processing. As novel sensors featuring advanced in-pixel processing capabilities emerge, we envision a paradigm shift toward performing increasingly complex visual processing directly in-pixel, reducing computational overhead downstream. We advocate for synthesizing high-level cues at the pixel level, enabling their off-sensor transmission to directly support downstream tasks more effectively than raw pixel readings. This paper conceptualizes a novel photometric rotation estimation algorithm to be distributed at pixel level, where each pixel estimates the global motion of the camera by exchanging information with other pixels to achieve global consensus. We employ a probabilistic formulation and leverage Gaussian Belief Propagation (GBP) for decentralized inference using messaging-passing. The proposed proposed technique is evaluated on real-world public datasets and we offer a in-depth analysis of the practicality of applying GBP to distributed rotation estimation at pixel level. |
| title | PixRO: Pixel-Distributed Rotational Odometry with Gaussian Belief Propagation |
| topic | Computer Vision and Pattern Recognition Distributed, Parallel, and Cluster Computing Multiagent Systems Robotics Image and Video Processing |
| url | https://arxiv.org/abs/2406.09726 |