As the price of photography and video equipment drops while quality and availability improve (think “GoPro”), images and video from tourism are becoming the most abundant and inexpensive sources of wildlife data. If these images could be widely obtained, rapidly analyzed and combined with related data (e.g., location, date, behavior), then scientists and conservation managers could benefit from larger and broader data sets. An increase in well managed data input and processing enables ... 阅读更多
As the price of photography and video equipment drops while quality and availability improve (think “GoPro”), images and video from tourism are becoming the most abundant and inexpensive sources of wildlife data. If these images could be widely obtained, rapidly analyzed and combined with related data (e.g., location, date, behavior), then scientists and conservation managers could benefit from larger and broader data sets. An increase in well managed data input and processing enables advances in analysis and modeling of animal populations, supporting deeper insight and better methods of protection for threatened and endangered animals. Unfortunately, the collection and management of wildlife imagery and metadata remains a largely ad hoc and academic exercise focused on moving small data sets (often in Excel and Access) into local, custom population studies for “one-off” analyses without long-term data curation or collaboration across borders and regions. This limits the scope, scale, repeatability, and ROI of the studies as they face the limits of their home-grown tools and IT capabilities.
Wild Me (www.wildme.org) - a 501(c)(3) non-profit organization focused on wildlife conservation - is uniquely comprised of IT professionals and computer scientists, advised by preeminent wildlife biologists. Wild Me’s experience providing advanced technology to a diverse array of wildlife studies and organizations falls into the technology category (artificial intelligence + computer vision) that the New York Times calls the “next big thing” for Silicon Valley. Our successful projects include:
Wildbook for Whale Sharks: http://www.whaleshark.org - a project launched in 2003 (among the earliest citizen-science efforts online) that brings collaborative, global-scale whale shark (Rhincodon typus) research onto the Web. We currently blend two computer vision algorithms to help identify individual whale sharks.
MantaMatcher, the Wildbook for Mantas: http://www.mantamatcher.org - a global site coordinating giant manta ray researchers and providing them with unique data management capabilities and computer vision to rapidly identify and resight mantas over time.
隐藏完整文本
