Calvin Hung

Feature Learning Based Approach for Weed Classification Using High Resolution Aerial Images from a Digital Camera Mounted on a UAV

The development of low-cost unmanned aerial vehicles (UAVs) and light weight imaging sensors has resulted in significant interest in their use for remote sensing applications. While significant attention has been paid to the collection, calibration, registration and mosaicking of data collected from small UAVs, the interpretation of these data into semantically meaningful information can still be a laborious task. A standard data collection and classification work-flow requires significant manual effort for segment size tuning, feature selection and rule-based classifier design. In this paper, we propose an alternative learning-based approach using feature learning to minimise the manual effort required. We apply this system to the classification of invasive weed species. Small UAVs are suited to this application, as they can collect data at high spatial resolutions, which is essential for the classification of small or localised weed outbreaks. In this paper, we apply feature learning to generate a bank of image filters that allows for the extraction of features that discriminate between the weeds of interest and background objects. These features are pooled to summarise the image statistics and form the input to a texton-based linear classifier that classifies an image patch as weed or background. We evaluated our approach to weed classification on three weeds of significance in Australia: water hyacinth, tropical soda apple and serrated tussock. Our results showed that collecting images at 5–10 m resulted in the highest classifier accuracy, indicated by F1 scores of up to 94%.

A Rotary-wing Unmanned Air Vehicle for Aquatic Weed Surveillance and Management

This paper addresses the novel application of an autonomous rotary-wing unmanned air vehicle (RUAV) as a cost-effective tool for the surveillance and management of aquatic weeds. A conservative estimate of the annual loss of agricultural revenue to the Australian economy due to weeds is in the order of A

Orchard fruit segmentation using multi-spectral feature learning

4 billion, hence the reason why weed control is of national significance. The presented system locates and identifies weeds in inaccessible locations. The RUAV is equipped with low-cost sensor suites and various weed detection algorithms. In order to provide the weed control operators with the capability of autonomous or remote control spraying and treatment of the aquatic weeds the RUAV is also fitted with a spray mechanism. The system has been demonstrated over inaccessible weed infested aquatic habitats.

A Feature Learning Based Approach for Automated Fruit Yield Estimation

This paper presents a multi-class image segmentation approach to automate fruit segmentation. A feature learning algorithm combined with a conditional random field is applied to multi-spectral image data. Current classification methods used in agriculture scenarios tend to use hand crafted application-based features. In contrast, our approach uses unsupervised feature learning to automatically capture most relevant features from the data. This property makes our approach robust against variance in canopy trees and therefore has the potential to be applied to different domains. The proposed algorithm is applied to a fruit segmentation problem for a robotic agricultural surveillance mission, aiming to provide yield estimation with high accuracy and robustness against fruit variance. Experimental results with data collected in an almond farm are shown. The segmentation is performed with features extracted from multi-spectral (colour and infrared) data. We achieve a global classification accuracy of 88%.

Cost-Effective Mapping Using Unmanned Aerial Vehicles in Ecology Monitoring Applications

This paper demonstrates a generalised multi-scale feature learning approach to multi-class segmentation, applied to the estimation of fruit yield on treecrops. The learning approach makes the algorithmflexible and adaptable to different classification problems, and hence applicable to a wide variety of tree-crop applications. Extensive experiments were performed on a dataset consisting of 8000 colour images collected in an apple orchard. This paper shows that the algorithm was able to segment apples with different sizes and colours in an outdoor environment with natural lighting conditions, with a single model obtained from images captured using a monocular colour camera. The segmentation results are applied to the problem of fruit counting and the results are compared against manual counting. The results show a squared correlation coefficient of R 2 = 0.81.

Mapping almond orchard canopy volume, flowers, fruit and yield using lidar and vision sensors

Ecology monitoring of large areas of farmland, rangelands and wilderness relies on routine map building and picture compilation, traditionally performed using high-flying surveys with manned-aircraft or through satellite remote sensing. Unmanned Aerial Vehicles (UAVs) are a promising alternative as a data collection platform due to the small-size, longer endurance and thus cost-effectiveness of these systems. Additionally UAVs can fly lower to the ground, collecting higher-resolution imagery than with manned aircraft or satellites. This paper discusses the development and experimental evaluation of systems and algorithms for airborne environment mapping, object detection and vegetation classification using low-cost sensor data including monocular vision collected from a UAV. Experimental results of the system are presented in multiple flights of our UAV system in three different environments and two different ecology monitoring applications, operating in remote locations in outback Australia.

“ShadowCut” - an unsupervised object segmentation algorithm for aerial robotic surveillance applications

Abstract This paper present a mobile terrestrial scanning system for almond orchards, that is able to efficiently map flower and fruit distributions and to estimate and predict yield for individual trees. A mobile robotic ground vehicle scans the orchard while logging data from on-board lidar and camera sensors. An automated software pipeline processes the data offline, to produce a 3D map of the orchard and to automatically detect each tree within that map, including correct associations for the same trees seen on prior occasions. Colour images are also associated to each tree, leading to a database of images and canopy models, at different times throughout the season and spanning multiple years. A canopy volume measure is derived from the 3D models, and classification is performed on the images to estimate flower and fruit density. These measures were compared to individual tree harvest weights to assess the relationship to yield. A block of approximately 580 trees was scanned at peak bloom, fruit-set and just before harvest for two subsequent years, with up to 50 trees individually harvested for comparison. Lidar canopy volume had the strongest linear relationship to yield with R 2 = 0.77 for 39 tree samples spanning two years. An additional experiment was performed using hand-held photography and image processing to measure fruit density, which exhibited similar performance ( R 2 = 0.71 ). Flower density measurements were not strongly related to yield, however, the maps show clear differentiation between almond varieties and may be useful for other studies.

Multi-class predictive template for tree crown detection

This paper introduces an unsupervised graph cut based object segmentation algorithm, ShadowCut, for robotic aerial surveillance applications. By exploiting the spatial setting of the aerial imagery, ShadowCut algorithm differs from state-of-the-art object segmentation algorithms ([1] [2] [3] [4] [5]) by not requiring a large number of labelled training data set, nor constant user interaction ([6] [7] [8]). In this paper it is shown that, by combining robotic navigation data and a shadow model, it is possible to provide these seed labels with a probabilistic sampling model for object segmentation in aerial imagery. Experiments were performed on aerial data sets consisting of data collected in outback Australia with an aerial robotic platform during an ecological surveillance mission, and aerial images with various natural targets from Google Earth. The segmentation results from the unsupervised ShadowCut algorithm are shown to be comparable with those from supervised graph cut algorithms.