Conference papers

With a limited number of workers or staff in the hospital, it is not possible to manually monitor all of the medical device in the hospital. Many medical devices were lost by mistake, many assets went unused because they were not well-stocked, and many assets were destroyed without recognizing it. This will undoubtedly be very negative to hospitals in terms of resources, which are often expensive, and will, of course, diminish the effectiveness and efficiency of medical services. The necessity for hospitals to modernize their technology is apparent. The rapid advancement of technology allows us to overcome these issues, in fact, IoT-based technology is now so advanced that paper-based technology must be gradually phased out. The technology is a real-time location system (RTLS), there are many different ways to implement this technology, one of them is to use Ultra-Wide band (UWB) technology, with this solution, hospitals can track the location of their medical device, as well as other information - this including the Transesophageal Echo (TEE) Probe. DWM1001 is one of the UWB modules that researchers can develop, but its deployment in hospitals still need more research and reliability. This study will address techniques for improving the reliability of anchor mapping and hybrid Wi-Fi solutions as backup solutions.

State-of-the-art self-supervised learning approaches for monocular depth estimation usually suffer from scale ambiguity. They do not generalize well when applied on distance estimation for complex projection models such as in fisheye and omnidirectional cameras. This paper introduces a novel multi-task learning strategy to improve self-supervised monocular distance estimation on fisheye and pinhole camera images. Our contribution to this work is threefold: Firstly, we introduce a novel distance estimation network architecture using a self-attention based encoder coupled with robust semantic feature guidance to the decoder that can be trained in a one-stage fashion. Secondly, we integrate a generalized robust loss function, which improves performance significantly while removing the need for hyperparameter tuning with the reprojection loss. Finally, we reduce the artifacts caused by dynamic objects violating static world assumptions using a semantic masking strategy. We significantly improve upon the RMSE of previous work on fisheye by 25% reduction in RMSE. As there is little work on fisheye cameras, we evaluated the proposed method on KITTI using a pinhole model. We achieved state-of-the-art performance among self-supervised methods without requiring an external scale estimation.