In our previous computer vision blog, we talked about how big data can be managed in the context of computer vision. As part of that discussion, we mentioned that selecting a smaller sample from a much later dataset can be a practical strategy for handling big data for computer vision applications. There are many ways to define a sample. These sampling strategies are not unique to computer vision but are rooted in statistics. This blog will look at more traditional methods based around random sampling, as well as a machine learning option and why these samples are important.
Think about this for a second: globally, men die six years earlier than women. To make it worse, the reasons are largely preventable. One in eight men across the world will be diagnosed with prostate cancer in their lifetime. Testicular cancer is the most common cancer among young men. Three quarters of suicides globally are men. Pretty shocking, right?
In recognition of Road Safety Week 2020, Abley partnered with the Australasian College of Road Safety (ACRS) to run a breakfast seminar on "Creating Safe Urban Environments".
Following the Christchurch earthquakes of 2010-2011 Tonkin + Taylor performed a large amount of geotechnical analysis for Christchurch City Council (CCC) and Environment Canterbury (ECan) to better understand possible liquefaction-induced damage under future earthquake events. Liquefaction is a natural process where earthquake shaking increases the water pressure in the ground causing some soils to behave like a fluid, resulting in temporary loss of soil strength. As shown by the Canterbury earthquakes it can cause significant damage to land, buildings, and infrastructure, through sediment being ejected to the ground surface, and subsequent ground settlement, ground cracking and lateral spreading. The geotechnical modelling included predictive assessments of liquefaction damage under various scenarios of earthquake intensity and groundwater level.
When working with big data it’s important to understand what makes data ‘big’, the limitations of working with it, and what can be done to combat these limitations. For the uninitiated, ‘big data’ doesn’t only refer to how much storage data may occupy, but it refers to a whole host of qualities.
On a mid-August afternoon, the request for an expression of interest (EOI) for Abley’s Corporate Rowing Team arrived. As many around the world these days, I was working flexibly, which happened to be in my living room just north of Christchurch. Initially, it was a “pass”, but from behind me came “click on it!” without me even aware that my partner was eavesdropping.
Geographically dispersed events, such as running, cycling or multisport races, and motorsport events like rally or targa present a unique challenge for spectators!
In my role as Data Science Researcher at Abley, working closely with my team we have identified that a computer vision solution could be used to detect traffic signs, which will add value and save time for the road safety work that we do here (see previous blog). The next step is to address the time-consuming process of data labelling. This blog will explain more about what data labelling is, why it’s an important step in preparing data, and the challenges involved for this project.