Blockchain-based Motion Detection in Smart Home with OpenCV and Raspberry PI
Home security is a serious problem that must be compromised. A simple mistake like forgetting to lock the door can result in tremendous material losses. There are several ways to help the homeowner mitigate the risk. One of them is by implementing a motion detection system. This model can help the homeowner detect unknown movement in a vacant house. Besides that, the recording from the sensor can help the investigation process. However, the current model had a problem where the data were modifiable. Thus, modified data could slow down the police investigation. This study aims to improve a computer vision-based motion detection model with blockchain-based that serves as end-to-end security. With this improvement, the model can detect invalidity. Besides data protection, this model also provided Telegram access for the end-users. According to the evaluation result, the proposed model successfully captured 300 recordings with a 98% success rate. In terms of performance, the model needed up to 42% of CPU in a multiprocessor environment. The memory usage for the process needed 12.94 MB, and the data usage was 107.18 MB on average. These facts concluded that the proposed model provided data protection with a good performance aspect for embedded systems.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a copyright form (JACTA) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).