Phoenix palms cover more than 1.3 million hectares in the Mediterranean, Middle East, and North Africa regions and they represent highly valued assets for economic, environmental, and cultural purposes. Despite their importance, information on the number of palm trees and the palm distribution across different scenes is difficult to obtain and, therefore, limited. In this work, we present the first region-wide spatial inventory of Phoenix dactylifera (date palm) and Phoenix canariensis (canary palm) trees, based on remote imagery from the Alicante province in Spain. A deep learning architecture that was based on convolutional neural networks (CNN) was implemented to generate a detection model able to locate and classify individual palms trees from aerial high-resolution RGB images. When considering that creating large labeled image datasets is a constraint in object detection applied to remote sensing data, as a strategy for pre-training detection models on a similar task, imagery and palm maps from the autonomous community of the Canary Islands were used. Subsequently, these models were transferred for re-training with imagery from Alicante. The best performing model was capable of mapping Phoenix palms in different scenes, with a changeable appearance, and with varied ages, achieving a mean average precision (mAP) value of 0.861. In total, 511,095 Phoenix palms with a probability score above 0.5 were detected over an area of 5816 km2. The detection model, which was obtained from an out-of-the-box object detector, RetinaNet, provides a fast and straightforward method to map isolated and densely distributed date and canary palms—and other Phoenix palms. The inventory of palm trees established here provides quantitative information on Phoenix palms distribution, which could be used as a baseline for long-term monitoring of palms’ conditions. In addition to boosting palm tree inventory across multiple landscapes at a large scale, the detection model demonstrates how image processing techniques that are based on deep learning leverage image understanding from remote sensing data.

基于深度学习的草坪树木检测是割草机器人智能化的前提和关键。目前缺乏公共的草坪树木数据集且现有的目标检测算法轻量化程度低,为解决在算力有限的割草机器人上实现草坪树木目标检测的难题,提出基于优化Tiny YOLOV4算法的草坪树木检测算法。首先,利用手机的拍照功能在草坪环境实地拍摄、制作两种草坪树木数据集;其次,在原Tiny YOLOV4算法基础之上,通过通道多尺度变换设计增强模块与轻量模块,结合多分辨率融合的方法,提出优化Tiny YOLOV4算法;通过训练优化后的算法模型实现割草机器人草坪树木的检测。试验结果表明:该优化Tiny YOLOV4算法对草坪环境下的树木特征检测的平均精度均值为80.59%,比Tiny YOLOV3和Tiny YOLOV4分别提高6.18%和0.61%。其中,树干的检测精度分别提高2.33%和0.22%,球状树木的检测精度分别提高10.04%和1.00%。模型大小为16.19 MB,轻量化程度分别提高51.10%和27.85%。

Existing deep convolutional neural networks (CNNs) require a fixed-size (e.g., 224 × 224) input image. This requirement is "artificial" and may reduce the recognition accuracy for the images or sub-images of an arbitrary size/scale. In this work, we equip the networks with another pooling strategy, "spatial pyramid pooling", to eliminate the above requirement. The new network structure, called SPP-net, can generate a fixed-length representation regardless of image size/scale. Pyramid pooling is also robust to object deformations. With these advantages, SPP-net should in general improve all CNN-based image classification methods. On the ImageNet 2012 dataset, we demonstrate that SPP-net boosts the accuracy of a variety of CNN architectures despite their different designs. On the Pascal VOC 2007 and Caltech101 datasets, SPP-net achieves state-of-the-art classification results using a single full-image representation and no fine-tuning. The power of SPP-net is also significant in object detection. Using SPP-net, we compute the feature maps from the entire image only once, and then pool features in arbitrary regions (sub-images) to generate fixed-length representations for training the detectors. This method avoids repeatedly computing the convolutional features. In processing test images, our method is 24-102 × faster than the R-CNN method, while achieving better or comparable accuracy on Pascal VOC 2007. In ImageNet Large Scale Visual Recognition Challenge (ILSVRC) 2014, our methods rank #2 in object detection and #3 in image classification among all 38 teams. This manuscript also introduces the improvement made for this competition.

针对现有目标检测算法在高压电力复杂巡检场景下电力部件与巡检缺陷检测精度较低的问题，提出一种基于尺度不变特征金字塔的输电线路缺陷检测方法。将主流目标检测方法用于该场景，对比得出RepPoints v2网络模型的检测精度最高。针对RepPoints v2中FPN结构不能有效提取跨层次间语义信息及角点验证过程中忽略尺度归一化的问题，结合高效通道注意力模块（ECA）与尺度均衡金字塔卷积（SEPC）提出了一种尺度不变特征金字塔结构SI-FPN（scale-invariant feature pyramid networks）。其中ECA注意力模块对FPN的特征进行通道级别的增强，之后SEPC从FPN中提取尺度不变特征并对跨层次的金字塔特征进行融合。通过在自建的包含绝缘子、防震锤、悬垂线夹、绝缘子自爆、防震锤脱落与鸟巢六类对象的数据集上进行训练测试表明，该方法在RepPoints v2的基准上提升1.9个百分点，mAP达到96.3%，检测精度远超当前基准检测模型，且所设计的SI-FPN模块可作为一种独立的结构改善其他检测模型，具有一定的通用性。

As the existing object detection algorithms have the problem of low detection accuracy of power components and inspection defects in complex inspection scenarios of high-voltage power, defect detection in transmission line based on scale-invariant feature pyramid networks is proposed. Firstly, by applying current baseline detection methods to the problem in this article, the RepPoints v2 networks has the highest accuracy. Secondly, as FPN structure cannot effectively extract cross-level semantic information and ignoring the scale normalization in the corner point verification process of RepPoints v2, the scale-invariant feature pyramid networks（SI-FPN） structure is proposed by combining the efficient channel attention（ECA） mechanism and the scale-equalizing pyramid convolution（SEPC）. In SI-FPN, the ECA attention module enhances the features of FPN at the channel level, and then SEPC extracts scale-invariant features from FPN and fuses cross-level pyramid features. Through training and testing on the self-built data set of six objects including insulator, shock hammer, suspension clamp, insulator self explosion, shock hammer falling off and bird’s nest, the proposed method improves 1.9 percentage points on the baseline of RepPoints v2, and the mAP reaches 96.3%. The detection accuracy is far beyond the current baseline detection models. Moreover, the SI-FPN module designed in this paper can be used as an independent structure to improve other detection models, which has certain universality.