Product

On-Camera Deep Learning

Firefly DL

-

Teledyne FLIR

Firefly DL - Teledyne FLIR

Deep learning is a powerful tool for system designers to quickly automate complex and subjective decision making and deliver higher quality products and improved productivity. Deploy your trained neural network to the FLIR Firefly DL with Neuro technology and reduce system cost and complexity by making decisions on-camera without host PC. With its very small size, low weight and power consumption, the Firefly DL camera is ideal for embedding into mobile, desktop, and handheld systems.

Product

Automatic Audio-Video Sync Detection

BATON® LipSync

-

Interra Systems, Inc.

BATON® LipSync - Interra Systems, Inc.

BATON® LipSync is an automated tool for lip sync detection and verification. BATON LipSync leverages image processing and machine learning (ML) technology and deep neural networks to automatically detect audio and video sync errors. Using BATON LipSync, broadcasters and service providers can accurately detect audio lead and lag issues in media content in order to provide a superior quality of experience (QoE) to viewers.

Product

Polynomial Neural Network Modeling

GNOSIS

-

Barron Associates

GNOSIS - Barron Associates

Many scientific, engineering, marketing, and economic phenomena are complex and difficult to model. Often, a large number of conditions that influence the input variables or an incomplete understanding of the underlying principles governing the system exacerbate the problem. The Barron Associates Generalized Networks for the Optimal Synthesis of Information Systems (GNOSIS) software suite provides a versatile and powerful method for modeling a variety of complex phenomena.

Product

SMARC

ROM-5820

-

Advantech Co. Ltd.

ROM-5820 - Advantech Co. Ltd.

The Advantech ROM-5820 stands as a state-of-the-art SMARC 2.1 Computer-on-Module, incorporating the robust NXP i.MX95 System-on-Chip (SOC). This SOC features an impressive configuration, with up to six Arm Cortex-A55 cores, accompanied by a dedicated Cortex-M7 and M33 real-time processor, and an added Neural Network accelerator. The ROM-5820 provides extensive connectivity options, including USB 2.0, USB 3.2 Gen1By1, 10 Gigabit Ethernet, MIPI-CSI, PCI Express, as well as both a dual-channel LVDS and a 4-lane MIPI-DSI Display interface. These remarkable features position the ROM-5820 as an exceptional choice for a wide variety of embedded applications.

Product

Artificial Intelligence And Machine Learning Testing

-

ImpactQA

ImpactQA

AI and ML testing framework can efficiently recognize pitfalls and with constant updates to the algorithms, it is feasible to discover even the negligible error. Essentially, Artificial Intelligence (AI) and Machine Learning (ML) tech are well-trained to process data, identify schemes and patterns, form and evaluate tests without human support. This is made possible with deep learning and artificial neural networks when a machine self-educates based on the given data sets or data extracted from an external source such as the web.

Product

Video Analysis Software

BrainChip Studio

-

BrainChip Inc.

BrainChip Studio - BrainChip Inc.

BrainChip Studio aids law enforcement and intelligence organizations to rapidly search vast amounts of video footage and identify patterns or faces. A result of over 10 years of R&D, it uses an artificial intelligence (AI) technology called a spiking neural network (SNN), a type of neuromorphic computing that simulates the functionality of the human visual tract. Because faces have unique identifying features, the software includes advanced facial detection, extraction and classification algorithms. The SNN technology enables BrainChip Studio to work on low-resolution video and requires only a 24x24 pixel image to detect and classify faces.

Product

ML/AI Low Power FPGA

iCE40 UltraPlus

-

Lattice Semiconductor

iCE40 UltraPlus - Lattice Semiconductor

*Flexible logic architecture with 2800 or 5280 4 input LUTs, customizable I/O, up to 80 kbits of embedded dual port memory and 1 Mbit of embedded single port memory*Ultra-low power advanced process with static current as low as 75 uA and 1-10 mA active current for most applications*High performance signal processing using DSP blocks with multiply and accumulate functions*Soft Neural Network IPs and compiler for flexible Machine Learning/AI implementation*FPGA design tools, demos and reference designs to kick start designs

Product

Multispectral Fixed Camera for Perimeter Protection

FH-Series ID

-

Teledyne FLIR

FH-Series ID - Teledyne FLIR

The FLIR FH-Series ID are ruggedized, multispectral fixed cameras that integrate industry-leading thermal imaging with 4K visible imaging to provide reliable intruder-detection capabilities for perimeter security. Built-in convolutional neural network (CNN) analytics accurately detect and classify human and vehicle threats moving at high or low speeds, minimizing false alarms and daily operations costs. Custom scheduling enables security operators to set intrusion analytics to run on visible streams during the day and on thermal streams throughout the night, establishing optimized coverage for any lighting condition.