History of Low-Power Computer Vision Challenge

2022 ◽  
pp. 17-24
Author(s):  
Yung-Hsiang Lu ◽  
Xiao Hu ◽  
Yiran Chen ◽  
Joe Spisak ◽  
Gaurav Aggarwal ◽  
...  
Keyword(s):  
2014 ◽  
Vol 626 ◽  
pp. 127-135 ◽  
Author(s):  
D. Jessintha ◽  
M. Kannan ◽  
P.L. Srinivasan

Discrete Cosine Transform (DCT) is commonly used in image compression. In the history of DCT, a milestone was the Distributed Arithmetic (DA) technique. Due to the technology dependency a multiplier-less computation was built with DA based technique. It occupied less area but the throughput is less. Later, due to the technology scaling, multiplier based architectures can be easily adapted for low-power and high-performance architecture. Fixed width multipliers [1]-[7] reduces hardware and time complexity. In this work, Radix 4 fixed width multiplier is adapted with DCT architecture due to low power consumption and saves 30% power. In order to reduce truncation errors caused during fixed width multiplication, an estimation circuit is designed based on conditional probability theory.


2022 ◽  
Author(s):  
George K. Thiruvathukal ◽  
Yung-Hsiang Lu ◽  
Jaeyoun Kim ◽  
Yiran Chen ◽  
Bo Chen
Keyword(s):  

Sensors ◽  
2014 ◽  
Vol 14 (4) ◽  
pp. 6247-6278 ◽  
Author(s):  
Gabriel García ◽  
Carlos Jara ◽  
Jorge Pomares ◽  
Aiman Alabdo ◽  
Lucas Poggi ◽  
...  

2021 ◽  
Vol 23 (12) ◽  
pp. 46-59
Author(s):  
B. Sathyabhama ◽  
◽  
B. Siva Shankari ◽  

Implantable Medical Devices (IMDs) reside within human bodies either temporarily or permanently, for diagnostic, monitoring, or therapeutic purposes. IMDs have a history of outstanding success in the treatment of many diseases, including heart diseases, neurological disorders, and deafness etc.,With the ever-increasing clinical need for implantable devices comes along with the continuous flow of technical challenges. Comparing with the commercial portable products, implantable devices share the same need to reduce size, weight and power. Thus, the need for device integration becomes very much imperative. There are many challenges faced when creating an implantable medical device. While this paper focuses on various techniques adapted to design a reliable device and also focus on the key electronic features of designing an ultra-low power implantable medical circuits for devices and systems.


This paper proposes a way to construct a financially cheap and fast object tracking using Raspberry Pi3. Multiple object detection is an important step in any computer vision application. Since the number of cameras included is more these gadgets are compelled by expense per hub, control utilization and handling power. We propose a tracking system with low power consumption. The framework is completely designed with python and OpenCV. The tracking quality and accuracy is measured using publicly available datasets.


Sign in / Sign up

Export Citation Format

Share Document