HazGTSimulator

HazGTSimulator tool and the relative dataset. ## An introduction to the files. ### 1. Dataset * UniformSampling: the result data of uniform sampling experiment * UniformSampling/Scene*/Hazard/UniformSampling.png: the curves of recall and precision * UniformSampling/Scene*/Hazard/WrongLabelsNumber.png: the curve of the number of perception errors * UniformSampling/Scene*/Hazard/Hazard_Value/GroundtruthLabels: the detection files of the groundtruth of a simulation * UniformSampling/Scene*/Hazard/Hazard_Value/labels: the detection files of yolov7 model * UniformSampling/Scene*/Hazard/Hazard_Value/flabels: the detection files of frcnn model * UniformSampling/Scene*/Hazard/Hazard_Value/Source: the images captured in a simulation * UniformSampling/Scene*/Hazard/Hazard_Value/Paint: the images with groundtruth labels * UniformSampling/Scene*/Hazard/Hazard_Value/Yolov7: the images detected by yolov7 * UniformSampling/Scene*/Hazard/Hazard_Value/FRCNN: the images detected by frcnn * UniformSampling/Scene*/Hazard/Hazard_Value/Hazards.json: the attributes file used in a simulation ### 2. Tool * HazGTSimulator: the simulator we used to generate traffic videos and images * use HazGTSimulator.exe to run it ### 3.data_picture1 * data_picture1/Genetic algorithm: Genetic algorithm experimental data * data_picture1/Genetic algorithm/faster rcnn: Experimental data of various hazard scenarios under the fast r-cnn model(Include confidence,detect number,undetect,misdetect) * data_picture1/Genetic algorithm/yolov7: Experimental data of various hazard scenarios under the yolov7 model(Include confidence,detect number,undetect,misdetect) * data_picture1/Gradient descent: Gradient descent algorithm experimental data * data_picture1/Gradient descent/faster rcnn: Experimental data of various hazard scenarios under the fast r-cnn model(Include confidence,detect number,undetect,misdetect) * data_picture1/Gradient descent/yolov7: Experimental data of various hazard scenarios under the yolov7 model(Include confidence,detect number,undetect,misdetect) * data_picture1/Random: Random algorithm experimental data * data_picture1/Random/faster rcnn: Experimental data of various hazard scenarios under the fast r-cnn model(Include confidence,detect number,undetect,misdetect) * data_picture1/Random/yolov7: Experimental data of various hazard scenarios under the yolov7 model(Include confidence,detect number,undetect,misdetect) * data_picture1/result_picture: * data_picture1/result_picture/faster rcnn: Picture of experimental results under the fast r-cnn model(The calculation formula for the y-axis scale is: (sum of confidence/(number of detect + number of undetect + number of misdetect)) * data_picture1/result_picture/yolov7: Picture of experimental results under the yolov7 model(The calculation formula for the y-axis scale is: (sum of confidence/(number of detect + number of undetect + number of misdetect)) ### 4.data_picture2 * data_picture2/data_fasterrcnn:Experimental data of various hazard scenarios under the fast r-cnn model(number of undetect and number of misdetect) * data_picture2/data_yolov7:Experimental data of various hazard scenarios under the yolov7 model(number of undetect and number of misdetect) * data_picture2/fasterrcnn:Data accumulation sum under the fast r-cnn model(number of undetect + number of misdetect) * data_picture2/yolov7:Data accumulation sum under the yolov7 model(number of undetect + number of misdetect) * data_picture2/faster rcnn_plot.png:Picture of experimental results under the fast r-cnn model(y-axis scale is Data accumulation sum above) * data_picture2/yolov7_plot.png:Picture of experimental results under the yolov7 model(y-axis scale is Data accumulation sum above)