Visual extensions and anomaly detection in the pNEUMA experiment with a swarm of drones

Treating Noise and Anomalies in Vehicle Trajectories From an Experiment With a Swarm of Drones

“…However, such errors can also occur on account of image processing or data processing. Spatially near but temporally far vehicles can show similar anomalies if passing through the same street obstructed from drone view at different times [6]. However, if the trajectories of vehicles are spatially and temporally apart, we expect little error correlation among them.…”

“…Except for the features that can be produced using the position information (speed, acceleration, and distance traveled), each vehicle type is available (car, taxi, motorcycle, bus, heavy and medium vehicle). We refer the reader to [5] for more details on the design of the experiment and to [6] for the recently released drone imagery. Since this dataset is also part of an open science initiative shared with the research community, these data are downloadable from https://open-traffic.epfl.ch.…”

“…Nevertheless, vehicles are not point objects but cover significant space; minor errors in the position can accumulate when speed or acceleration variables are calculated. Furthermore, the urban driving environment is more complex than highways due to the increased heterogeneity of vehicle classes, traffic signals, congestion, intersections, parking vehicles, and occlusion due to high-rise buildings and trees [6]. All these factors could introduce noise and anomalies or outliers in the extracted trajectories from the ©2023 IEEE.…”

Automated Road Defect and Anomaly Detection for Traffic Safety: A Systematic Review

“…In addition to image processing, CV combines artificial intelligence (AI) approaches to derive meaningful information from images and videos [ 54 ]. When merged with Global Positioning Systems (GPS), telescopes, binoculars, closed-circuit television (CCTV), vehicle-mounted video recorders and cameras, and low-cost mobile cameras, image processing-based visual surveillance can significantly increase the efficiency of ARDAD systems [ 18 , 40 , 55 , 56 , 57 ]. Maya et al [ 58 ] proposed a delayed long short-term memory (dLSTM)-based technique that is trained in a normal state and predicts abnormalities depending on the defined in Equation (2).…”

“…In this systematic review, studies from 2000 to 2023 are selected to capture the evolution of ARDAD methods and technologies over the past two decades. The selected time frame covers crucial developments, including a mathematical morphological method at the turn of the millennium [ 38 ], automated anomaly detection a decade later [ 39 ], and sophisticated surveillance techniques employing UAV swarms by 2023 [ 40 ].…”