Breaking News
Comments
Newest First | Oldest First | Threaded View
twilson207
User Rank
Rookie
re: Tensilica vs. Ceva in imaging/vision IP core battle
twilson207   9/5/2013 1:16:58 PM
NO RATINGS
Actually there is a 3rd player in the mix in the form of CogniVue with their Image Cognition Processing (ICP) technology.  CogniVue has been designing vision processing IP for low power embedded and mobile applications for several years and launched the ICP architecture in 2010, making the IP available in their own SOC.  In 2012 CogniVue licensed their ICP APEX processing core to Freescale (http://media.freescale.com/phoenix.zhtml?c=196520&p=irol-newsArticle&ID=1734693&highlight=) for vision processing in Automotive safety applications.   CogniVue is now a technology licensing company squarely focused on embedded vision processing, and in fact was one of the founding members of the Embedded Vision Alliance in 2011.  The comments in the article about the complexities of vision processing are quite accurate and the ICP APEX processing core is specifically architected to "hide" memory access latency while optimizing the vision processing pipeline.  Check us out at www.cognivue.com.  

SimonCMorris
User Rank
Rookie
Tensilica vs Ceva vs CogniVue
SimonCMorris   9/5/2013 1:06:32 PM
NO RATINGS
Article completely left out CogniVue Corporation which was a founding member of EVA before CEVA and Tensilica announced their vision cores.  CogniVue's APEX image cognition processor (ICP) technology addresses what is mentioned in this article as key  - an efficient  processor architecture for vision processing is not just about massively parallel pixel processing, but about creating vision friendly data structures, minimizing data movement and somehow achieving na efficiently pipelined implementation of very complex vision algorithms.

junko.yoshida
User Rank
Blogger
re: Tensilica vs. Ceva in imaging/vision IP core battle
junko.yoshida   2/13/2013 6:29:26 PM
NO RATINGS
This is a processor core tailored to the imaging pipeline. Just as Tensilica used its software profiling tools to create an optimized CPU for its HiFi family of audio DSPs, Tensilica engineers, this time around, "created a specialized DSP with an instruction set that reduces the cycle count of the key embedded vision algorithms," according to Linley Group's Gardner.

krisi
User Rank
CEO
re: Tensilica vs. Ceva in imaging/vision IP core battle
krisi   2/13/2013 4:21:55 PM
NO RATINGS
Pretty useful cores...how are they different from DSP cores?

kjdsfkjdshfkdshfvc
User Rank
Rookie
re: Tensilica vs. Ceva in imaging/vision IP core battle
kjdsfkjdshfkdshfvc   2/13/2013 2:40:14 PM
NO RATINGS
Wow, that's stuff that's over my head. http://bit.ly/dI3hcF



Flash Poll
EE Life
Frankenstein's Fix, Teardowns, Sideshows, Design Contests, Reader Content & More
Engineer's Bookshelf
Caleb Kraft

The Martian: A Delightful Exploration of Math, Mars & Feces
Caleb Kraft
3 comments
To say that Andy Weir's The Martian is an exploration of math, Mars, and feces is a slight simplification. I doubt that the author would have any complaints, though.

The Engineering Life - Around the Web
Caleb Kraft

Surprise TOQ Teardown at EELive!
Caleb Kraft
Post a comment
This year, for EELive! I had a little surprise that I was quite eager to share. Qualcom had given us a TOQ smart watch in order to award someone a prize. We were given complete freedom to ...

Design Contests & Competitions
Caleb Kraft

Join The Balancing Act With April's Caption Contest
Caleb Kraft
54 comments
Sometimes it can feel like you're really performing in the big tent when presenting your hardware. This month's caption contest exemplifies this wonderfully.

Engineering Investigations
Caleb Kraft

Frankenstein's Fix: The Winners Announced!
Caleb Kraft
8 comments
The Frankenstein's Fix contest for the Tektronix Scope has finally officially come to an end. We had an incredibly amusing live chat earlier today to announce the winners. However, we ...

Top Comments of the Week
Like Us on Facebook
EE Times on Twitter
EE Times Twitter Feed

Datasheets.com Parts Search

185 million searchable parts
(please enter a part number or hit search to begin)