Real-time vehicle detection for traffic monitoring by applying a deep learning algorithm over images acquired from satellite and drone

Abstract

PurposeThe purpose is to design a system in which drones can control traffic most effectively using a deep learning algorithm.Design/methodology/approachDrones have now started entry into each facet of life. The entry of drones has made them a subject of great relevance in the present technological era. The span of drones is, however, very broad due to various kinds of usages leading to different types of drones. Out of the many usages, one usage which is presently being widely researched is traffic monitoring as traffic monitoring can hover over a particular area. This paper specifically brings out the basic algorithm You Look Only Once (YOLO) which may be used for identifying the vehicles. Consequently, using deep learning YOLO algorithm, identification of vehicles will, therefore, help in easy regulation of traffic in streetlights, avoiding accidents, finding out the culprit drivers due to which traffic jam would have taken place and recognition of a pattern of traffic at various timings of the day, thereby announcing the same through radio (namely, Frequency Modulation (FM)) channels, so that people can take the route which is the least jammed.FindingsThe study found that the object(s) detected by the deep learning algorithm is almost the same as if seen from a naked eye from the top view. This led to the conclusion that the drones may be used for traffic monitoring, in the days to come, which was not the case earlier.Originality/valueThe main research content and key algorithm have been introduced. The research is original. None of the parts of this research paper has been published anywhere.

Communication via quad/hexa-copters during disasters

“…The other functions (not illustrated in Figure 1) based on which the placement of drones in the air was also studied are generally based on communication stability when the user rides on the communication channel. The communication channel's stability depends upon the quality and bandwidth of the channel from the source end, namely, the drone (relay) to the destination end (Vohra et al ., 2022). The stability also depends upon the termination equipment, namely, opti-mux, Synchronous Transfer Module (STM) 1, loop-mux.…”

Adversarial Examples in Visual Object Tracking in Satellite Videos: Cross-Frame Momentum Accumulation for Adversarial Examples Generation

“…Visual object tracking (VOT) refers to the process of finding a target to be tracked in the first frame of a video, with the aim of accurately locating the target's position in subsequent frames and precisely outlining it with anchor box. Compared to traditional VOT methods, satellite video object tracking benefits from a wider shooting range, often resulting in higher efficiency in monitoring targets in applications such as military reconnaissance [1][2][3], traffic monitoring [4][5][6], and wildlife tracking [7][8][9].…”