Abstract
Automatic flood detection may be an important component for triggering damage control systems and minimizing the risk of social or economic impacts caused by flooding. Riverside images from regular cameras are a widely available resource that can be used for tackling this problem. Nevertheless, state-of-the-art neural networks, the most suitable approach for this type of computer vision task, are usually resource-consuming, which poses a challenge for deploying these models within low-capability Internet of Things (IoT) devices with unstable internet connections. In this work, we propose a deep neural network (DNN) architecture pruning algorithm capable of finding a pruned version of a given DNN within a user-specified memory footprint. Our results demonstrate that our proposed algorithm can find a pruned DNN model with the specified memory footprint with little to no degradation of its segmentation performance. Finally, we show that our algorithm can be used in a memory-constraint wireless sensor network (WSN) employed to detect flooding events of urban rivers, and the resulting pruned models have competitive results compared with the original models.
Highlights
The algorithm was employed for pruning the DeepLabv3 deep neural network (DNN) models [17], considered the best semantic segmentation models currently available, and the results show that this strategy can find pruned models within the specified amount of memory with good segmentation performance
We propose a heuristic that allows the reduction of the memory footprint of DNNs applied in semantic segmentation tasks; We propose a pruning algorithm that finds DNN models with a user-specified amount of memory, allowing their deployment on memory-constrained devices, such as Internet of Things (IoT)
We developed a DNN architecture pruning algorithm in which the memory footprint of a given DNN model is reduced by randomly eliminating convolutional filters
Summary
Flood risk is the probability that exposure to flooding will cause negative consequences, ranging from economic losses to social and health issues [1]. When this risk is not negligible, flood management solutions become of paramount importance, and different types of technologies have been proposed for this aim [2]. We present the theoretical background used in our proposed algorithm It first explains semantic segmentation through deep neural network (DNN) models. It shows how we are using semantic segmentation to detect the level of urban rivers. Its main difference from instance segmentation is that it cannot locate individual instances of a specific object [18]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
