Home

February | March | April | May | June | July | August

February

• MRes 2nd project proposal;
• Road Safety for Cyclists in London project allocation;

March

• Start of 2nd project;
• Background reading on: cycling benefits (economical, environmental, safety, equalitarian and health), road safety indicators (accident rate, injury rate and fatality rate) and risk factors (intersections, vehicle speed, road width...);

April

• Background reading on: deep learning, convolution neural networks, object detection, image segmentation, bash commands, tensorflow and pytorch;

May

• Research on the available datasets containing road related detected objects/segmented images: ADE20K, MS Coco, Cityscapes and Open Images V6.
• Several object detection and image segmentation models were tested in small image datasets locally. Including YOLOv4, YOLOv5 (s, m, l and x versions) and DeepLabv3+ for object detection. PSPNet101 and Gluon CV;

June

• Based on the accuracy, performance and documentation of the previous models, YOLOv5 and PSPNet101 were selected as the object detection and image segmentation models.
• Previous models were run in the complete Google Street View imagery dataset (approximately, 1/2 million images from all London LSOAs).

July

• Data visualization. Correlation matrices (across the multiple detected objects), pie charts (providing an overview on the most common objects and labelled pixels), histograms (similarly to the previous) and LSOA maps (representing the distribution of the 30 MS Coco classes in Greater London) were defined as main sources for visualizing all data from the project;

August

• Article write-up.