Deep learning networks have shown great success in several computer vision applications, but its implementation in natural land cover mapping in the context of object-based image analysis (OBIA) is rarely explored area especially in terms of the impact of training sample size on the performance comparison. In this study, two representatives of deep learning networks including fully convolutional networks (FCN) and patch-based deep convolutional neural networks (DCNN), and two conventional classifiers including random forest and support vector machine were implemented within the framework of OBIA to classify seven natural land cover types. We assessed the deep learning classifiers using different training sample sizes and compared their performance with traditional classifiers. FCN was implemented using two types of training samples to investigate its ability to utilize object surrounding information. Our results indicate that DCNN may produce inferior performance compared to conventional classifiers when the training sample size is small, but it tends to show substantially higher accuracy than the conventional classifiers when the training sample size becomes large. The results also imply that FCN is more efficient in utilizing the information in the training sample than DCNN and conventional classifiers, with higher if not similar achieved accuracy regardless of sample size. DCNN and FCN tend to show similar performance for the large sample size when the training samples used for training the FCN do not contain object surrounding label information. However, with the ability of utilizing surrounding label information, FCN always achieved much higher accuracy than all the other classification methods regardless of the number of training samples.

Measurement of plant characteristics is still the primary bottleneck in both plant breeding and crop management. Rapid and accurate acquisition of information about large plant populations is critical for monitoring plant health and dissecting the underlying genetic traits. In recent years, high-throughput phenotyping technology has benefitted immensely from both remote sensing and machine learning. Simultaneous use of multiple sensors (e.g., high-resolution RGB, multispectral, hyperspectral, chlorophyll fluorescence, and light detection and ranging (LiDAR)) allows a range of spatial and spectral resolutions depending on the trait in question. Meanwhile, computer vision and machine learning methodology have emerged as powerful tools for extracting useful biological information from image data. Together, these tools allow the evaluation of various morphological, structural, biophysical, and biochemical traits. In this review, we focus on the recent development of phenomics approaches in strawberry farming, particularly those utilizing remote sensing and machine learning, with an eye toward future prospects for strawberries in precision agriculture. The research discussed is broadly categorized according to strawberry traits related to (1) fruit/flower detection, fruit maturity, fruit quality, internal fruit attributes, fruit shape, and yield prediction; (2) leaf and canopy attributes; (3) water stress; and (4) pest and disease detection. Finally, we present a synthesis of the potential research opportunities and directions that could further promote the use of remote sensing and machine learning in strawberry farming.

The purpose of this study is to examine the use of multi-resolution object-based classification methods for the classification of Unmanned Aircraft Systems (UAS) images of wetland vegetation and to compare its performance with pixel-based classification approaches. Three types of classifiers (Support Vector Machine, Artificial Neural Network and Maximum Likelihood) were utilized to classify the object-based images, the original 8-cm UAS images and the down-sampled (30 cm) version of the image. The results of the object-based and two pixel-based classifications were evaluated and compared. Object-based classification produced higher accuracy than pixel-based classifications if the same type of classifier is used. Our results also showed that under the same classification scheme (i.e. object or pixel), the Support Vector Machine classifier performed slightly better than Artificial Neural Network, which often yielded better results than Maximum Likelihood. With an overall accuracy of 70.78%, object-based classification using Support Vector Machine showed the best performance. This study also concludes that while UAS has the potential to provide flexible and feasible solutions for wetland mapping, some issues related to image quality still need to be addressed in order to improve the classification performance.