Header menu link for other important links
Spot a Spot—Efficient Parking System Using Single-Shot MultiBox Detector
Thakkar Y, Sutreja A, Kumar A, Taneja S,
Published in Springer Singapore
Volume: 1079
Pages: 931 - 939
In this paper, a method has been proposed to allot a parking spot after detecting it using single-shot multibox detector (SSD). The CCTV cameras will capture n number of frames and pass it through single neural network that is SSD. This will help in fetching details of the vacant parking spot. Subsequent convolution and non-maximum suppression will make the most accurate box around the detected object. Further, the coordinates will be fetched and will be allotted to the incoming cars. This will save time and fuel especially in leveled parking areas. The industrialization of the world, increment in population, moderate-paced city improvement, and bungle of the accessible parking spot have brought about parking-related issues. There is a critical requirement of clever, efficient, fast, protected, dependable, and secured framework for this paper which will be used for getting the vacant parking spots. The method proposed in this paper is better than the already existing one which is ultrasonic radiations and sensors as it is faster, and the drawback of an object/vehicle not being recognized due to its presence in the blind spot is overcome. SSD captures more number of frames compared with YOLO and CNN. It is best for large object recognition and real-time processing which will provide a secured framework for faster and efficient parking allotting. © Springer Nature Singapore Pte Ltd 2020.
About the journal
JournalData powered by TypesetAdvances in Intelligent Systems and Computing Data Engineering and Communication Technology
PublisherData powered by TypesetSpringer Singapore
Open Access0