Imaging

Reducing Drift in Stereo Visual Odometry

The drift was reduced from an uncorrected 47 cm to just 7 cm. Visual odometry (VO) refers to the estimation of vehicle motion using onboard cameras. A common mode of operation utilizes stereovision to tri angulate a set of image features, track these over time, and infer vehicle motion by computing the apparent point cloud motion with respect to the cameras. It has been observed that stereo VO is subject to drift over time.

Posted in: Imaging, Briefs

Read More >>

Frame Grabber Deployed in Robomotive Humanoid Robot

Robomotive and other humanoid robots equipped with 3D vision sensors are playing an increasing role in industrial automation, including in smaller binpicking set-ups where parts are constantly changing.

Posted in: Imaging, Application Briefs

Read More >>

Measuring Motion with Imaging Software

High-speed photography is as much of an engineering tool as an oscilloscope, spectrum analyzer, or logic analyzer. The photographic technique enables us to visualize and analyze motion, especially motion that is too fast for the human eye or conventional cameras to perceive.

Posted in: Imaging, Articles

Read More >>

LED Illumination in Simulation and Training

Since its inception, projection has been the dominant technology for displaying large, high-resolution images. Over the years, projectors have evolved to keep pace with advances in computer graphics and video sources, following the trends toward ever higher resolutions and ever larger screens.

Posted in: Imaging, Articles

Read More >>

Reducing Drift in Stereo Visual Odometry

The drift was reduced from an uncorrected 47 cm to just 7 cm. Visual odometry (VO) refers to the estimation of vehicle motion using onboard cameras. A common mode of operation utilizes stereovision to tri angulate a set of image features, track these over time, and infer vehicle motion by computing the apparent point cloud motion with respect to the cameras. It has been observed that stereo VO is subject to drift over time.

Posted in: Imaging, Briefs

Read More >>

Resource-Constrained Application of Support Vector Machines to Imagery

Fast computation of the SVM decision function over an image using minimal RAM. Machine learning techniques have shown considerable promise for automating common visual inspection tasks. For example, Support Vector Machine (SVM) classifiers that have been learned from labeled training data deliver strong detection performance both for finding human faces in photographs and locating geologic landforms such as craters and volcanoes in planetary images gathered by spacecraft. However, SVMs are computationally expensive to apply to an image using the traditional spatial scanning method in which a rectangular window is slid across the image one pixel at a time and the SVM is evaluated on each patch of pixels under the window. The new software uses small fast Fourier transforms (FFTs) and the overlap- and-add technique from signal processing to quickly and efficiently compute the exact SVM decision function over an entire image using minimal random access memory (RAM).

Posted in: Imaging, Briefs

Read More >>

Improving Absorption Measurements through Light Source Selection

Stray light limits the maximum absorbance level achievable with a given spectrometer. Once the stray light limit is reached, sample dilution or a smaller pathlength is required to measure more concentrated samples. In this application note, we show the impact of stray light on the maximum absorbance level and describe how optimizing the choice of light source can minimize stray light and increase the maximum absorbance measured.

Posted in: Imaging, White Papers

Read More >>

3D Visualization Technologies: Seeing a World of Opportunity

Industries as diverse as architecture, engineering, construction, advertising, and medical have all incorporated an array of 3D visualization technologies into their design, development, and production processes. A rapidly expanding library of 3D modeling tools, 3D content, and 3D printing materials have made design more cost-effective and expedited the product-to-market process. But how exactly do 3D visualization technologies work? Taking a closer look at the science behind the innovation reveals a striking convergence in which state-of-the-art research processes meet a growing understanding of visual communication.

Posted in: Imaging, Articles

Read More >>

Precision Electronics and Laser Optics Expand Thermal Applications

Thermal imagers allow a user to see an object’s heat signature, and heat provides an entirely different set of performance data than the visible spectrum available to the naked eye. A fully radiometric camera will calculate a temperature value for every pixel seen on screen. The technician uses the thermal colors on screen to look for differences in temperature, between previous states or like components, without actually coming into direct contact with the device under test.

Posted in: Imaging, Articles

Read More >>

Ophthalmology Imaging: The Importance of Color Reproduction

Lumenera recently partnered with an ophthalmology diagnostic device manufacturer that required a camera for integration into its product. The goal was to obtain sharp retinal fundus images with accurate color reproduction for documentation, sharing, and storage of their results. A date stamp was also needed for later review and diagnosis.

Posted in: Imaging, Application Briefs

Read More >>