The European Processor Initiative (EPI) is developing a processor for various sectors, including the automotive industry. To benchmark the new processor, EPI uses a test vehicle to demonstrate different use cases, like semi-autonomous driving. In this paper, we focus on object detection and describe the use cases in the perception stage of autonomous driving. Therefore, we introduce four applications that include face recognition, blind spot detection, near-range object detection and far-range spatial perception to cover a wide range of different domains. Each use case runs on a different architecture representing future domains of the EPI processor, allowing for optimal utilization and performance. Our evaluation shows that all use cases can be mapped on the future EPI platform. The performance of the image processing tasks such as blind spot detection meets real-time requirements and runs at over 30 FPS. The face recognition task can process an image with low-power consumption, allowing for battery-powered inference. Finally, we validate our results and findings using a BMW X5 car as a real-world demonstrator.