感測器解析 Part 2
設計資料精簡 (Data Reduction)的電腦視覺演算法
(Designing Computer Vision Algorithms for Data Reduction)

近年來由於電腦視覺演算法朝強健以及高效率發展,以攝影機為基礎的系統已成為高級輔助駕駛系統(ADAS, advanced drive assistance systems)主要的途徑。這些視覺系統快速地變成主動式安全系統的重要構成元件。

在本演講中,我們將展示如何進行邊緣設備的分析並精簡資料的維度,以輕鬆地在雲端匯集資料。尤其,我們將說明MATLAB®如何被運用在電腦視覺化的基礎分析及ADAS元件的設計,像是以電腦視覺演算法進行行人偵測,以及以立體視覺(stereo-vision)為基礎的防撞設計等。除此之外,我們還會展示如何針對開發的演算法自動產生程式碼,然後在嵌入式的感測器平台上運行程式碼。

Camera-based systems have become a key approach to advanced driver assistance systems (ADAS) due to recent advancements in robust and efficient computer vision algorithms. These vision systems are rapidly becoming a key component of active safety systems.

In this session, we show how to develop analytics and reduce data dimensionality at the edge node for easier aggregation in the Cloud. Specifically, we demonstrate how MATLAB® can be used to design computer vision-based analytics and ADAS components such as pedestrian detectors and stereo-vision-based collision avoidance using computer vision algorithms. Additionally, we will show how to automatically generate code for the developed algorithms and run them on an embedded sensor platform.