Rura
Municipal sewers require regular inspections to ensure their proper functioning. One of the most cost-effective methods for this is using CCTV with operators controlling remotely operated crawlers which move inside the sewer pipes to collect footage. Analyzing this footage to create standardized sewer condition reports is a time-consuming and cognitively repetitive process prone to human error. To overcome these limitations, we harnessed the power of Artificial Intelligence (AI) to automate video inspection data analysis and streamline report generation, revolutionizing the efficiency and accuracy of sewer network assessments.
The Problem
Implementing AI for drainage network inspection presented several complex challenges. Visual observations in video inspections often contained numerous artifacts and noise, such as overexposed surfaces, water splashes, and dirt patterns resembling structural defects. Imbalances, errors, and high variability in the available data made the task even more challenging. Additionally, the computational intensity of video data analysis constrained the choice of architectures and solutions.
Our Solution
We have successfully deployed an AI-powered SaaS solution that automates the detection and classification of sewer defects and faults, delivering standardized reports. The platform enables seamless video inspection uploads through an API, web interface, or direct SFTP connection to the platform backend. It is powered by an AI model consisting of an ensemble of specialized neural networks, dynamically selected based on temporal and spatial context information recognized in the early analysis stages, optimizing resource utilization.
To enhance the efficiency of neural network training, we first trained the deep neural network in unsupervised mode using large volumes of unlabelled data. This produced information-rich label embeddings, leading to more effective supervised training in the subsequent stage. To account for non-standard situations and novel data, we integrated out-of-distribution detection principles and graceful degradation techniques. Instances with detected out-of-distribution data can be forwarded to operators for further verification, ensuring robust analysis and enhancing the system’s adaptability.
The Outcome
Our cloud-based, AI-first SaaS solution marks a significant breakthrough in sewer inspection processes, delivering comprehensive inspection reports within 24 hours. With a user-friendly interface, clients gain seamless access to view, analyze, and export inspection results, enhancing their operational capabilities.
Other cases
01
Gamma
Radionuclide medical diagnostics detects how well internal organs function. The most common techniques are SPECT Tomography and Gamma Camera scans. Recording the radiation emitted by an injected radioactive tracer from within the body, they construct a 3D image – dynamic scintigram – showing how well the organs work. We used AI to analyse these images
02
Valkyrie
Commercial adoption of Unmanned Aerial Vehicles is growing. Various commercial use cases, from industrial inspections to mobile security applications are springing up every day. Bringing AI technologies onboard a UAV offers unprecedented opportunities to revolutionise the commercial use of UAVs
03
Lucent
Single alkali halide crystals (boules) are indispensable in a number of a very demanding applications in high energy, nuclear, space and medical physics. Growing large crystals is an expensive and complex process with strict requirements placed on their physical properties. We used AI to improve crystallisation process quality control
05
Porcus
Our services were requested by an innovative B2B platform for the pig growing industry. A simple yet powerful production management tool, it connects owners, caregivers and veterinarians allowing them to track the pig growing process from start to finish and keep track of animal health concerns in real time
06
Kronos
Our mission was to help an innovative company fuse wearable technology and cutting-edge computational methods to deliver personalized advice on achieving peak performance. Understanding an individual’s chronotype – their sleep and wake phases – is crucial for predicting performance and productivity throughout the day. To meet the challenge of optimizing productivity, even beyond natural chronotypes, […]
