Author: sravan

How to conquer distortion and converge towards higher quality sensor fusion.

Distortion is an important factor to consider in image feature tracking, image stitching, point cloud registration, and fusing data from multi-modal sensors. Distortion can occur due to various factors such as lens imperfections, camera calibration errors, and atmospheric effects. It can cause image features to appear misaligned, leading to inaccuracies in the final results. Image…
Read more

How to stitch multiple cameras together on a moving vehicle

Image stitching is the process of combining multiple images together to create a seamless panorama or a large-scale image. This technique is commonly used in photography, virtual reality, and mapping applications. In this blog, we will take a deep dive into the concepts of image stitching, including sensor and vehicle frame of reference, origin point,…
Read more

Down in the trenches with Robert, a Geospatial Ops Manager for a large ADAS team

As a Geospatial Ops Manager, Robert is responsible for running product operations for a large Advanced Driver Assistance Systems (ADAS) team at an Original Equipment Manufacturer (OEM). This includes managing multiple teams that handle different tasks such as lane segmentation, free space detection, map creation, and map updating. However, Robert has been facing several challenges…
Read more

How to use The Potential of Unsupervised Auto-Labeling: A Guide to Building Scalable MLOps Pipelines

Building a scalable MLOps pipeline for unsupervised machine learning can be a challenging task for engineers, but with the right approach, it can be done efficiently. One key aspect of building a scalable pipeline is to use unsupervised machine learning algorithms to auto-label images and point cloud data. This can be done by segmenting the…
Read more

Unlock the Power of Vision Analytics with Fleet Queries: A Guide to Optimizing Your ADAS Fleet

Advanced Driver Assistance Systems (ADAS) are becoming increasingly prevalent in today’s vehicles, and with that comes the need for efficient and effective data management. One powerful tool for managing data from a fleet of ADAS-equipped vehicles is the fleet query. A fleet query is a command that is sent to a fleet of ADAS vehicles,…
Read more

Revolutionizing L3 ADAS: Harnessing the Power of Test Harnesses and MLOps for Safe and Reliable Automotive Technology

Regression testing is a crucial aspect of developing L3 Advanced Driver Assistance Systems (ADAS) technology. It involves re-testing the entire system or parts of it, after changes or modifications have been made, to ensure that the changes did not introduce any new bugs or defects. This is particularly important for ADAS systems, which rely on…
Read more

What is ADAS (Level 2 and below)?

Advanced Driver Assistance System (ADAS) is a technology that helps drivers to drive safely and efficiently. It is a combination of sensors, cameras, and other technologies that work together to help drivers monitor their speed, maintain their lane, and avoid collisions. ADAS can be found in many modern cars, and it is becoming increasingly popular…
Read more

Revolutionizing the Road: How Hyperspec AI’s Fleet Learning Approach is Changing the Game for Detecting Lane Merges on the Highway

Automating the process of data annotation has been a long-standing challenge in the field of machine learning, especially when it comes to detecting lane merges on the highway. The traditional approach of manually labeling data is not only costly in terms of time and resources, but it also hinders the ability to quickly detect lane…
Read more

Navigating the Road to Success: How Abstracting Maps for Self-Driving Cars Ensures Safe and Efficient Operation

Self-driving cars rely heavily on maps to navigate and make decisions while on the road. These maps must be accurate, detailed, and up-to-date in order for the car to operate safely and efficiently. However, as self-driving cars become more prevalent, it has become clear that the way maps are created and used needs to change.…
Read more

Uncovering ADAS Failure Cases: The Importance of Edge Vision Analytics and Fleet Queries in Vehicle Safety

Collecting failure cases from a fleet of L3 ADAS vehicles is a crucial task in ensuring the safety and reliability of these systems. With the increasing use of advanced driver assistance systems (ADAS) in vehicles, it is important to have a reliable and efficient method for collecting and analyzing data from these systems. One way…
Read more

Drive smarter, not harder: The OODA loop’s way to advanced driving assistance

The OODA loop, or Observe, Orient, Decide, and Act loop, is a decision-making framework that was developed by military strategist and United States Air Force Colonel John Boyd. The OODA loop is based on the idea that in any situation, the side that can cycle through the loop faster and more effectively will have a…
Read more

Navigating the complexities of coordinate frames: A guide to understanding the differences in Three.js, ROS, and Unreal Engine

Coordinate frames are an important aspect of robotics and computer graphics, as they determine the position and orientation of objects in 3D space. However, different platforms and software libraries use different conventions for their coordinate frames, which can lead to confusion and errors when working with multiple systems. Three.js, ROS, and Unreal Engine are all…
Read more

Jane, a superstar ADAS engineer

As the sun rose over the bustling city, Jane, an Adas engineer at a leading autonomous vehicle company, woke up to the familiar sound of her alarm clock. She knew that today would be a challenging day, filled with long hours and intense problem-solving. Jane arrived at the office and immediately got to work on…
Read more

Unsupervised Machine Learning and Speed Ups in Labeling

Unsupervised machine learning is a type of machine learning that involves training a model on a dataset without providing it with labeled examples. Instead, the model is asked to discover the underlying structure of the data on its own. One popular technique for unsupervised machine learning is clustering, which involves grouping similar data points together.…
Read more

Javascript, Caching to Optimize Network Traffic

Browsers use caching to temporarily store resources locally on the device, such as HTML, CSS, and JavaScript files, images, and videos. This allows the browser to quickly access the resources without having to make additional requests to the server. One way browsers can enable device-side caching is through the use of local storage. Local storage…
Read more

Training PackNet-SFM with RGB + PointCloud Data

Fusing time synchronized RGB camera images with point cloud data is a powerful approach for training a PackNet-SFM (Structure from Motion) model in PyTorch. This technique combines the benefits of both RGB images and point cloud data to improve the accuracy and robustness of the SFM model. In this article, we will discuss the various…
Read more

Roadmap Compression via Streamlining MLOps Infrastructure and its Impacts on ADAS programs

Advanced Driver Assistance Systems (ADAS) are becoming increasingly important in the automotive industry as they offer a wide range of features that enhance the safety and comfort of the driving experience. However, the development and deployment of ADAS systems can be a complex and time-consuming process. Traditional hand-coded algorithms and feature engineering, while they have…
Read more

Market size of ADAS development tools. Bottoms up and top down calculations

ADAS: 20.73 billion in 2021 to 74.57 billion by 2030 with a CAGR of 14.2% AI: 119.78 billion in 2022 to $ 1.6 trillion by 2030 with a registered CAGR of 38.1% AI within ADAS: $6 billion in 2022 to $600 billion by 2032, at a CAGR of 55% The market size of Advanced Driver Assistance…
Read more

Integrating Federated Learning into CVAT & MLFlow

Federated learning is a machine learning technique that enables the training of models on decentralized data, without the need for the data to be centralized in one location. Instead, data is distributed across a number of different devices or edge devices, such as smartphones or IoT devices, and the model is trained by aggregating updates…
Read more

WebGPU and Federated Learning with FedML, a Killer Combo

WebGPU is a new technology that allows developers to take advantage of the power of the GPU (graphics processing unit) in modern browsers. It allows for faster and more efficient processing of complex tasks, including machine learning algorithms. One of the key benefits of WebGPU is its ability to support federated learning. Federated learning is…
Read more

Data backhauling tips and techniques to save on bandwidth & latency

Data backhauling refers to the process of transferring data from one location to another, typically from a remote or geographically dispersed location to a central location or “backhaul.” This process is often used in industries such as transportation, where data from vehicles or other mobile assets is collected and sent back to a central location…
Read more

Training a Model in MLFlow from CVAT label data

CVAT (Computer Vision Annotation Tool) is an open source tool developed by Intel that allows users to label and annotate images and video data for training machine learning models. MLFlow is an open source platform for managing the end-to-end machine learning lifecycle. It provides tools for tracking experiment runs, organizing code, and reproducing runs, among…
Read more

Integrating CVAT annotation into MLFlow

CVAT (Computer Vision Annotation Tool) is an open-source annotation tool for computer vision tasks that allows users to label and manage large datasets quickly and efficiently. Integrating CVAT with an MLFlow framework can streamline the data labeling process and make it easier to track and analyze the performance of your machine learning models. Here is…
Read more

Dimensionality reduction and how it helps reduce the search space by leveraging known information

Removing dimensions or making invariant features is a technique used to reduce the search space in a problem by eliminating certain variables or making them irrelevant. This can be especially useful in LiDAR slam, which has a 6Dof search space (x, y, z, roll, pitch, yaw). By reducing the dimensions, the number of permutations in…
Read more

Data balancing to remove data bias, do a deep dive on different approaches

Data balancing is the process of ensuring that a machine learning dataset is representative of the real-world population from which it is drawn. This is important because if a dataset is biased, then the machine learning model that is trained on that dataset will also be biased. Bias in machine learning models can lead to…
Read more

How data structures impact time complexity of code

Data structures are the foundation of efficient algorithms and play a crucial role in determining the time complexity of a piece of code. Time complexity refers to the amount of time it takes for an algorithm to complete, and it is a measure of how the runtime of an algorithm grows as the input size…
Read more

Techniques to Boost True Positive Rates using Independent Combinatorics

True positive rates, or the proportion of positive cases that are correctly identified, are an important consideration in many areas. One way to boost true positive rates is to utilize independent combinatorics, a set of techniques that involve combining multiple independent pieces of information or evidence to make a decision. Here are some specific techniques…
Read more

Improving Model Performance from 99.9% to 99.999999%

Artificial intelligence (AI) has come a long way in recent years, with many industries adopting it to improve efficiency and productivity. However, there is always room for improvement, and one area where AI can be further enhanced is in terms of accuracy. Currently, many AI systems have an accuracy rate of around 99.9%, which is…
Read more

Loose Coupling vs Tight Coupling; Best of Both Worlds

Loose coupling and tight coupling refer to the degree of interdependence between different components in a system. In software development, loose coupling refers to the design of components that can operate independently of one another and do not rely heavily on the internal details of other components. Tight coupling, on the other hand, refers to…
Read more

Real-time vs Cloud-Based Architectures for Autonomous Systems

In the field of autonomous systems, the choice between real-time and cloud-based architectures can have significant consequences for the performance, reliability, and cost of a system. In this article, we will explore the key differences between these two approaches and the trade-offs involved in choosing one over the other. We will also discuss how cloud-based…
Read more