摘要
Robotics&Machine Learning Daily News的新闻记者兼新闻编辑-研究人员在Robotics S中详细介绍了新的数据。根据Ne wsRx记者从弗吉尼亚州夏洛茨维尔发回的新闻报道，研究表明：“节肢动物的眼睛是有效的生物视觉系统，用于跟踪物体和宽视野，因为它们的结构独特；然而，与哺乳动物的眼睛不同，由于他们的单目线索，他们很难获得静态物体的D EPTH信息。新闻记者从弗吉尼亚大学的研究中获得了一句话：“因此，大多数节肢动物依靠运动视差在三维(3D)空间跟踪物体。唯一的是螳螂(Mantodea)使用复合结构眼睛和一种立体视觉，能够在3D空间实现物体识别。这里，利用立体耦合人工复眼模拟螳螂的视觉系统,实现了三维空间中三维时空目标的感知与跟踪,实现了响应速度快、响应时间短、数据存储传输量小、功耗低。我们利用突触装置和联合分裂学习算法对系统边缘的视觉信息进行处理，设计和制作的立体人工复眼提供了高能效、精确的时空目标传感和光流传输，其均方根误差为0.3cm，传感和跟踪仅消耗近4毫焦耳。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Researchers detail new data in robotic s. According to news reporting originating from Charlottesville, Virginia, by Ne wsRx correspondents, research stated, “Arthropods’ eyes are effective biological vision systems for object tracking and wide field of view because of their stru ctural uniqueness; however, unlike mammalian eyes, they can hardly acquire the d epth information of a static object because of their monocular cues.” The news journalists obtained a quote from the research from University of Virgi nia: “Therefore, most arthropods rely on motion parallax to track the object in three-dimensional (3D) space. Uniquely, the praying mantis (Mantodea) uses both compound structured eyes and a form of stereopsis and is capable of achieving ob ject recognition in 3D space. Here, by mimicking the vision system of the prayin g mantis using stereoscopically coupled artificial compound eyes, we demonstrate d spatiotemporal object sensing and tracking in 3D space with a wide field of vi ew. Furthermore, to achieve a fast response with minimal latency, data storage/t ransportation, and power consumption, we processed the visual information at the edge of the system using a synaptic device and a federated split learning algor ithm. The designed and fabricated stereoscopic artificial compound eye provides energy-efficient and accurate spatiotemporal object sensing and optical flow tra cking. It exhibits a root mean square error of 0.3 centimeter, consuming only ap proximately 4 millijoules for sensing and tracking.”
NETL
NSTL