Autonomous aerial harvesting is a highly complex problem because it requires numerous interdisciplinary algorithms to be executed on mini low-powered computing devices. Object detection is one such algorithm that is compute-hungry. In this context, we make the following contributions: ( i ) Fast Fruit Detector (FFD), a resource-efficient, single-stage, and postprocessing-free object detector based on our novel latent object representation ( LOR ) module, query assignment, and prediction strategy. FFD achieves $\mathbf {100}$ FPS $@$ FP $\mathbf {32}$ precision on the latest $\mathbf {10}$ W NVIDIA Jetson-NX embedded device while co-existing with other time-critical sub-systems such as control, grasping, SLAM, a major achievement of this work, ( ii ) a method to generate vast amounts of training data without exhaustive manual labelling of fruit images since they consist of a large number of instances, which increases the labelling cost and time, and ( iii ) an open-source fruit detection dataset having plenty of very small-sized instances that are difficult to detect. Our exhaustive evaluations on our and MinneApple dataset show that FFD, being only a single-scale detector, is more accurate than many representative detectors, e.g. FFD is better than single-scale Faster-RCNN by $\mathbf {10.7}$ AP, multi-scale Faster-RCNN by $\mathbf {2.3}$ AP, and better than latest single-scale YOLO-v $\mathbf {8}$ by $\mathbf {8}$ AP and multi-scale YOLO-v $\mathbf {8}$ by $\mathbf {0.3}$ while being considerably faster.

中文翻译：

---

适用于空中抓取低功耗设备的高速探测器

自主空中收割是一个非常复杂的问题，因为它需要在微型低功率计算设备上执行大量跨学科算法。对象检测就是这样一种需要大量计算的算法。在此背景下，我们做出以下贡献：（ i) 快速水果检测器 (FFD)，一种资源高效、单级且无需后处理的对象检测器，基于我们新颖的潜在对象表示（ 洛尔 ) 模块、查询分配和预测策略。 FFD 实现$\mathbf {100}$ FPS$@$FP $\mathbf {32}$精确到最新$\mathbf {10}$W NVIDIA Jetson-NX嵌入式设备同时与控制、抓取、SLAM等其他时间关键的子系统共存，是这项工作的重大成果，（ ii）一种生成大量训练数据的方法，无需对水果图像进行详尽的手动标记，因为它们由大量实例组成，这增加了标记成本和时间，并且（ iii）一个开源水果检测数据集，其中包含大量难以检测的非常小的实例。我们对我们和 MinneApple 数据集的详尽评估表明，FFD 只是一个单尺度检测器，比许多代表性检测器更准确，例如 FFD 比单尺度 Faster-RCNN 更好$\mathbf {10.7}$AP，多尺度 Faster-RCNN$\mathbf {2.3}$AP，比最新的单尺度 YOLO-v 更好$\mathbf {8}$经过$\mathbf {8}$AP 和多尺度 YOLO-v $\mathbf {8}$经过$\mathbf {0.3}$同时速度要快得多。