TAPPAS

Hailo has developed TAPPAS to streamline the development and deployment of edge applications that require high performance. This reference applications software package helps customers accelerate their time to market by reducing the amount of time and effort spent on development. TAPPAS includes a user-friendly GStreamer-based set of fully functional application examples that incorporate pipeline elements and pre-trained AI tasks. These examples are built on top of advanced Deep Neural Networks that showcase the best-in-class throughput and power efficiency of Hailo’s AI processors. In addition, TAPPAS illustrates how Hailo’s system integration works by showcasing specific use cases on predefined software and hardware platforms. By utilizing TAPPAS, customers can simplify integration with Hailo’s runtime software stack and have a starting point to fine-tune their applications.

Hailo’s TAPPAS Template Applications And Solutions for high-performance edge application development and deployment

TAPPAS, an object detection app: A high-resolution video feed of a busy speedway is processed in real time on the Hailo-8™ AI Processor with high detection accuracy.

TAPPAS out-of-the-box versatile apps include:

Multi-Camera Multi-Person (RE-ID)

Learn More

Multi-Camera Multi-Person (RE-ID)

Tracking specific people across multiple cameras in the pipeline with multiple streams utilizing model scheduling

Tiling

Learn More

Tiling

License Plate Recognition (LPR)

Learn More

License Plate Recognition (LPR)

Automatic license plate recognition application based on a complex pipeline utilizing model scheduling

Multi Stream Object Detection

Learn More

Multi-stream Object Detection

Detection apps with several available neural networks, delivering unique functionalities and supporting multiple streams

Hailo Tappas Classification

Learn More

Classification

Ready-made ResNet-50-based application, trained on ImageNet

Hailo Tappas Depth Estimation

Learn More

Depth Estimation​

Depth estimation is prominently used for assisted driving, enabling smart automotive cameras to turn a 2D video input into a 3D to sense how close and far objects are. Use your own network or use the pre-built FastDepth 2 model, pre-trained on KITTI depth

Learn More

Semantic Segmentation

Commonly used for ADAS applications, in automotive cameras , semantic segmentation enables the vehicle to decide where the road, sidewalk, other vehicles and pedestrians are. The pre-built TAPPAS semantic segmentation app demonstrates Hailo-8's high compute capacity by processing a Full HD input video stream in real-time. The app is based on an FCN8-resnet1_18 network pre-trained on CitysScapes

Hailo Tappas Multiple Object Tracking

Learn More

Multiple Object Tracking

An advanced versatile model that detects and tracks multiple simultaneously-moving people

Facial Detection and Recognition

Learn More

Facial Detection and Recognition

Apps for face recognition and detection app for security and authentication applications

Pose Estimation

Learn More

Pose Estimation

Pose Estimation apps can be a significant building block for commercial and consumer applications. From recognizing emergency situations at home or on the factory floor, to analyzing customer behavior for better business outcomes. Use your own pose estimation network or use the pre-built CenterPose model pre-trained on COCO

Object Detection

Learn More

Object Detection

Detection on one video file source by running a single-stream object detection pipeline

Instance Segmentation

Learn More

Instance Segmentation

A YOLACT-based model that identifies, outlines and colors different objects and persons