SBIR Phase II: An Automated Drone-Based Cattle Monitoring Service

SBIR 第二阶段：基于无人机的自动化牛群监控服务

• 批准号: 2036703
• 负责人: Shoshana Ginsburg
• 金额: $ 99.74万
• 依托单位: IMAGINAG TECH, LLC
• 依托单位国家: 美国
• 项目类别: Cooperative Agreement
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-06-15 至 2024-05-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2036703&HistoricalAwards=false
• 关键词: SBIR; Phase; II; Automated; Drone

The broader impact of this Small Business Innovation Research (SBIR) Phase II project will result from the development of disruptive technologies that use drones and artificial intelligence to monitor livestock. Almost 75% of United States cattle are purchased by taking out bank loans, and lenders need to audit cattle inventories for collateral verification and appraisal purposes. Additionally, more than 140,000 ranchers need to monitor their herds and detect cattle illnesses before infections spread. The proposed technology will leverage aerial imaging and artificial intelligence to count cattle, characterize cattle weight, and diagnose cattle illnesses up to one week before clinical symptoms appear. The ability to count herds regularly will enable ranchers to discover cattle rustling issues early and provide banks with a reliable way to perform collateral verification on ranches and feedlots, ensuring that banks can continue extending livestock operations the loans that they need to survive. The ability to detect cattle illnesses early is expected to reduce cattle mortalities, the economic cost of antibiotic use, and possibly antibiotic resistance in humans. Ultimately, the proposed technology that will be developed for monitoring cattle promises to also transform the way that land and marine wildlife, fisheries, and endangered species are monitored.This Small Business Innovation Research (SBIR) Phase II project will provide cattlemen and bankers with an efficient way to detect and count cattle on pastures and ranches, estimate livestock weight, and identify ill cows before they spread infection further. Despite daily monitoring of cattle herds, small discrepancies and losses are undiscoverable, and bovine illnesses are often left undetected until they spread, infecting more cattle and requiring large-scale administration of antibiotics. Machine learning and image processing tools will be developed that (a) automatically analyze natural and thermal drone images to count cattle on multi-topography ranches and estimate livestock weight and (b) discriminate between healthy and ill cattle based on aerial radiometric imaging. The outcomes will be (1) a ready, drone-agnostic solution for counting cattle and estimating their weight and (2) a pilot-tested drone-and-software system for monitoring cattle health via radiometric imaging and notifying cattlemen about cows with suspected illness in real-time.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

这个小企业创新研究（SBIR）第二阶段项目的更广泛影响将来自使用无人机和人工智能监测牲畜的颠覆性技术的发展。 美国近75%的牛是通过银行贷款购买的，贷款人需要审计牛的库存，以进行抵押品核查和评估。 此外，超过140，000名牧场主需要监测他们的牛群，并在感染蔓延之前发现牛的疾病。 该技术将利用航空成像和人工智能来计算牛的数量，描述牛的体重，并在临床症状出现前一周诊断牛的疾病。 定期清点牛群的能力将使牧场主能够及早发现牛群问题，并为银行提供一种可靠的方式来对牧场和饲养场进行抵押品核查，确保银行能够继续向牲畜经营提供生存所需的贷款。 早期检测牛疾病的能力预计将降低牛的死亡率、抗生素使用的经济成本，并可能降低人类的抗生素耐药性。 最终，将开发的用于监测牛的拟议技术也有望改变陆地和海洋野生动物，渔业和濒危物种的监测方式。这个小型企业创新研究（SBIR）第二阶段项目将为牧牛人和银行家提供一种有效的方法来检测和计数牧场和牧场上的牛，估计牲畜体重，并在进一步传播感染之前识别患病奶牛。 尽管每天都对牛群进行监测，但微小的差异和损失是无法弥补的，牛的疾病往往在蔓延之前未被发现，感染更多的牛，需要大规模施用抗生素。 将开发机器学习和图像处理工具，以（a）自动分析自然和热无人机图像，以计算多地形牧场的牛数并估计牲畜重量，（B）根据航空辐射成像区分健康和生病的牛。结果将是（1）一个现成的，无人机不可知解决方案，用于对牛进行计数并估计其重量，以及（2）经过试点测试的无人机和软件系统，用于通过辐射成像监测牛的健康状况，并在真实的中通知养牛人有关疑似疾病的牛。该奖项反映了NSF的法定使命，并通过使用基金会的知识价值和更广泛的影响审查进行评估，被认为值得支持的搜索.