Camouflage evaluation typically involves human visual search and detection experiments that are time-consuming and expensive. Hence, there is a need for models that compute camouflage effectiveness from digital imagery. Convolutional neural networks are a powerful tool for automatic object detection and recognition. We investigated whether such a network (YOLO) can also provide a measure of camouflage effectiveness that is related to human perception. To this end, human performance measures of camouflage effectiveness such as detection time and target conspicuity were obtained in observer experiments and compared with the performance of the (standard, i.e. pre-trained) YOLO-V4-tiny algorithm. YOLO provides the probability that a detected object is correctly classified, and this is adopted as our measure of camouflage effectiveness. We compared the YOLO-predicted classification probability for a person in camouflage clothing moving through rural and urban scenes to human detection performance. Overall, camouflage effectiveness predicted by YOLO correlates with human observer performance. At close distances, YOLO’s classification performance appears sensitive to high-contrast shape-breaking elements of a camouflage pattern. This suggests that YOLO may be adapted to assess camouflage effectiveness for a wide range of applications, such as evaluating or optimizing one’s signature and predicting optimal hiding locations in a given environment. Further research is required to fully establish YOLO’s limitations and applicability for this purpose.

The relationships among the potential causes of a car and motorcycle collision involving turn maneuvers as well as the perception of rear and front turn signal (on/off) configuration is examined in this paper. The investigation has been based on data pooled from the answers of a survey proposed to 136 people, with special regards to the correct detection of indicators aspect. Experimental videos have been realized during the tests campaign, both in urban and suburban areas, using a 360-camera attached to a motorcyclist’s helmet, reproducing vehicular conflicts able to potentially generate crash risks. The detection of the blinker was combined with other factors (e.g. age, gender, location of the test site, presence of the car behind tester vehicles and if the bikers are also habitual car or bike drivers) in a stepwise logistic regression that modelled the odds of detecting the turn signal turned on as a function of all of these factors. The results suggest the existence of a connection between the detection of the turn signal aspect and some of the variables considered (e.g. age, being a cyclist or a car driver and the presence of a protecting car).