# Smart Video Capsule Endoscopy: Raw Image-Based Localization for Enhanced GI Tract Investigation

arXiv: https://arxiv.org/abs/2507.23398 · HTML: https://mlsanity.com/paper/2507.23398/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 25 references that are in the map.
- First posted on arXiv 31 Jul 2025.

## Builds on (most cited first, 3 of 3)

- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [Precise localization within the GI tract by combining classification of CNNs and time-series analysis of HMMs](https://mlsanity.com/paper/2310.07895/) (2023)
- [Systematic Hardware Integration Testing for Smart Video-based Medical Device Prototypes](https://mlsanity.com/paper/2504.19533/) (2025)

## Built on by (most cited first, 2 of 2)

- [Image Compression with Bubble-Aware Frame Rate Adaptation for Energy-Efficient Video Capsule Endoscopy](https://mlsanity.com/paper/2604.25464/) (2026)
- [CapsuleMotion: A Lightweight Real-Time Visual Motion Predictor for Capsule Endoscopy](https://mlsanity.com/paper/2609.15367/) (2026)

## Abstract (arXiv)

For many real-world applications involving low-power sensor edge devices deep neural networks used for image classification might not be suitable. This is due to their typically large model size and require- ment of operations often exceeding the capabilities of such resource lim- ited devices. Furthermore, camera sensors usually capture images with a Bayer color filter applied, which are subsequently converted to RGB images that are commonly used for neural network training. However, on resource-constrained devices, such conversions demands their share of energy and optimally should be skipped if possible. This work ad- dresses the need for hardware-suitable AI targeting sensor edge devices by means of the Video Capsule Endoscopy, an important medical proce- dure for the investigation of the small intestine, which is strongly limited by its battery lifetime. Accurate organ classification is performed with a final accuracy of 93.06% evaluated directly on Bayer images involv- ing a CNN with only 63,000 parameters and time-series analysis in the form of Viterbi decoding. Finally, the process of capturing images with a camera and raw image processing is demonstrated with a customized PULPissimo System-on-Chip with a RISC-V core and an ultra-low power hardware accelerator providing an energy-efficient AI-based image clas- sification approach requiring just 5.31 μJ per image. As a result, it is possible to save an average of 89.9% of energy before entering the small intestine compared to classic video capsules.