Efficient Semantic Segmentation for Visual Bird's-eye View Interpretation
This work addresses the need for efficient semantic segmentation in applications like visual bird's-eye view interpretation on limited hardware, representing an incremental improvement.
The paper tackled the problem of real-time semantic segmentation for visual bird's-eye view interpretation by reducing runtime and hardware requirements, achieving a decrease in runtime through parallelization of the ArgMax layer and applying channel pruning to the ENet model.
The ability to perform semantic segmentation in real-time capable applications with limited hardware is of great importance. One such application is the interpretation of the visual bird's-eye view, which requires the semantic segmentation of the four omnidirectional camera images. In this paper, we present an efficient semantic segmentation that sets new standards in terms of runtime and hardware requirements. Our two main contributions are the decrease of the runtime by parallelizing the ArgMax layer and the reduction of hardware requirements by applying the channel pruning method to the ENet model.