Google Research presents a new real-time approach to object detection that exploits the efficiency of cascade classifiers with the accuracy of deep neural networks. Pedestrian detectors is very important as it relates to a variety of applications including advanced driver assistance systems, or surveillance systems. The need for very high-accurate and real-time speed is crucial that can be relied on and are fast enough to run on systems with limited compute power.
The research team combined a fast cascade with a cascade of deep neural networks which is both very fast, running in real-time at 67 milliseconds on GPU per image or 15 frames per second. Their approach was trained using the publicly available ‘cuda-convnet2’ code running on an NVIDIA Tesla K20 GPU.
Real-Time Pedestrian Detection using Cascades of Deep Neural Networks
Aug 06, 2015
Discuss (0)

Related resources
- GTC session: Rapid Development of Industrial-Scale Object Detection (Presented by Lockheed Martin) (Spring 2023)
- GTC session: AI Models Made Simple Using TAO (Spring 2023)
- GTC session: Real-Time Early Collision Warning System for Snowplows using NVIDIA Jetson with Sensor Fusion (Spring 2023)
- Webinar: Deep Learning for Medical Imaging: Real-World Challenges and Opportunities
- Webinar: Autonomous Driving at Scale: Architect and Deploy Object Detection Inference Pipelines
- Webinar: Accelerate YOLOv5 and Custom AI Models in ROS with NVIDIA Isaac