Application of novel machine learning techniques and high speed 3D vision algorithms for real time detection of fruit

该项目解决了水果的自动检测，这是开发水果采摘机器人的基本要求，重点是草莓。它与工业战略的以下支柱密切相关：（1）投资于科学，研究和创新，以及（2）发展技能。如果成功的话，这种方法可以推广到其他水果作物，但是通过专注于草莓，我们正在解决英国水果行业研究和发展的首要任务之一。该行业非常担心英国脱欧的影响可能会威胁到农民工采摘水果作物的可用性。此外，它面临着巨大的价格和成本压力。尽管英国脱欧，但年龄的长期人口统计数据将减少农业劳动力的可用性。然而，尽管存在这些问题，消费者仍然希望持续并可能增加新鲜营养水果的供应。这促使该行业寻求新的手段来提高整体生产力。包括视觉系统、机器人和自主系统在内的新型数字技术被视为该行业的潜在游戏规则改变者。视觉系统可用于评估和感知作物，以实现更好的决策支持;机器人和自主系统提供了提高生产力的新手段。这些问题不仅适用于所有软质水果和顶部水果，而且更广泛地适用于整个新鲜农产品行业。然而，所有的采摘和视觉系统都依赖于复杂算法的开发，这些算法被开发用于真实的实时识别、测量和定位水果。这些系统的开发并不简单，特别是在背景光水平和质量可能在瞬间发生变化的户外环境中。在这里，我们将部署新的机器学习技术来检测，定位和测量（大小和颜色）水果在真实的时间。这项工作从根本上支撑了所有作物采摘机器人的发展。

This project addresses automated detection of fruit, which is an essential requirement for developing robotics for fruit picking, focusing on strawberry. It aligns closely with the following pillars of the industrial strategy: (1) investing in science, research and innovation, and (2) developing skills. If successful, this methodology could be generalised to other fruit crops, however by focussing on strawberry we are addressing one of top priorities in research and development of the UK fruit industry. The industry is extremely concerned that the impact of Brexit may threaten the availability of migrant workers to pick fruit crops. Furthermore, it is under significant price and cost pressure. Notwithstanding Brexit, the longer-term demographics of age will reduce the availability of on farm labour. However irrespective of these issues, the consumer will still want an on-going and likely increasing supply of fresh nutritious fruit. This is driving the industry to seek new means to drive overall productivity. Novel digital technologies including vision systems, robotics and autonomous systems are seen as potential game changers for the sector. Visions systems can be used to assess and sense the crop to enable better decision support; robotics and autonomous systems offer new means to drive productivity. These issues apply to all soft and top fruits, but also more widely across the whole fresh produce sector. However, all picking and vision systems are dependent on the development of complex algorithms developed to identify, measure and locate fruit in real time. The development of these systems is not trivial, especially in outdoor environments where the back ground light level and quality can change within an instant. Here we will deploy novel machine learning technologies to detect, locate and measure (size and colour) fruit in real time. This work fundamentally underpins the development of all crop-picking robots.