We developed a personal computer-based machine vision system and applied it in computer-aided potato inspection. The system was able to classify 50 potato images per second for potato weight, cross-sectional diameter, shape, and color, which are the important criteria in sorting potatoes in practice
Sequential localisation and map-building for real-time computer vision and robotics
โ Scribed by Andrew J. Davison; Nobuyuki Kita
- Publisher
- Elsevier Science
- Year
- 2001
- Tongue
- English
- Weight
- 150 KB
- Volume
- 36
- Category
- Article
- ISSN
- 0921-8890
No coin nor oath required. For personal study only.
โฆ Synopsis
Reviewing the important problem of simultaneous localisation and map-building, we emphasise its genericity and in particular draw parallels between the often divided fields of computer vision and robot navigation. We compare sequential techniques with the batch methodologies currently prevalent in computer vision, and explain the additional challenges presented by real-time constraints which mean that there is still much work to be done in the sequential case, which when solved will lead to impressive and useful applications. In a detailed tutorial on map-building using first-order error propagation, particular attention is drawn to the roles of modelling and an active methodology. Finally, recognising the critical role of software in tackling a generic problem such as this, we announce the distribution of a proven and carefully designed open-source software framework which is intended for use in a wide range of robot and vision applications.
๐ SIMILAR VOLUMES
## Computation of Orientational Filters for Real-time Computer Vision Problems III: Steerable System and VLSI Architecture rientational filters have been used frequently for computer vision problems. Despite their strength in various vision problems, their use has been limited in real-time applica