Time filter

Source Type

American Fork, UT, United States

Fowers S.G.,Brigham Young University | Fowers S.G.,Microsoft | Lee D.-J.,Brigham Young University | Ventura D.A.,Brigham Young University | And 2 more authors.
Journal of Aerospace Information Systems | Year: 2013

Feature point matching is an important step for many vision-based unmanned-aerial-vehicle applications. This paper presents the development of a new feature descriptor for feature point matching that is well suited for micro unmanned aerial vehicles equipped with a low-resource, compact, lightweight, low-power embedded vision sensor. The Basis Sparse-Coding Inspired Similarity descriptor uses theory taken from sparse coding to provide an efficient image feature description method for frame-to-frame feature point matching. This descriptor requires simple mathematical operations, uses comparatively small memory storage, and can support color and grayscale feature descriptions. It is an excellent candidate for implementation on low-resource systems that require real-time performance, where complex mathematical operations are prohibitively expensive. To demonstrate its performance, the feature matching result was used to calculate a frame-to-frame homography that is essential to unmanned-aerial vehicle applications such as pose estimation and obstacle detection for navigation. The proposed descriptor was tested on two video sequences and one dataset of real aerial images. Experimental results show that, along with performing in situations where existing complex descriptors cannot be used, the Basis Sparse-Coding Inspired Similarity descriptor also performs slightly better than these other methods on the task of homography calculation. Our experimental results and analysis show that the Basis Sparse-Coding Inspired Similarity descriptor is an excellent candidate for a resource-limited vision sensor for micro unmanned aerial vehicles.

Agency: Department of Agriculture | Branch: | Program: SBIR | Phase: Phase I | Award Amount: 100.00K | Year: 2014

Agricultural sorting and grading is most commonly preformed primarily through the use of human resources. Farm workers sort crops by hand through visual inspection. This process is expensive and highly subjective. In addition the labor force is susceptible to human error which can impact the quality of the resulting data. The outcome of this project will be to increase efficiencies in the grading and sorting process through the use of visual automation. With our current algorithm, cameras and computers are used to sort crops, which increases the overall accuracy of the agricultural grading and sorting processe, contributing to increases in efficiency as well as profitability. Our current installations of this technology have decreased their labor costs by as much as 47%. Phase one of this project will have the outcome of improving our current process by allowing two seperate functions, grading and sorting, to be preformed on the same machine. We will do this by increasing the availabe functions of the algorithm, including but not limited to color, and increasing the accuracy and efficiency of the algorithm.

Agency: Department of Agriculture | Branch: | Program: SBIR | Phase: Phase II | Award Amount: 499.90K | Year: 2015

In order for America to remain competitive in the world market in agriculture production and processing it must continue to innovate and create technologies that decrease the cost of food production. If America can do so, it maintains the ability to produce high quality products. Sorting and grading is an expensive and time consuming part of agriculture production and decreasing its cost through technology will aid in making America competitive on the world market.In order to make the most impact, technology needs to be widely available to specialty crops and not only large markets with access to large sums of capital. Our phase II research improves the functionality of an existing produce grading and sorting mechanical system. Our system helps aid farmers and agricultural processing companies improve the overall quality of their processing by increasing the accuracy of their sorting and grading process. We attach cameras to existing mechanical carrier systems, and the cameras feed data to computers. The computers than feed quality information back to the mechanical system, allowing the crop to be sorted based on quality, size, and other characteristics. This automated process allows them to decrease their labor costs, and improve time to markets. Thus allowing them to be more competitive, creating prosperity in rural communities.

Zhang D.,Sun Yat Sen University | Lillywhite K.D.,Smart Vision Works, Llc | Lee D.-J.,Brigham Young University | Tippetts B.J.,Smart Vision Works, Llc
Computers and Electronics in Agriculture | Year: 2014

Shrimp has become one of the most favorite seafood in recent years. As worldwide shrimp production grows, shrimp quality evaluation becomes a critical task for the seafood and aquaculture industries. Automatic evaluation of shrimp shape is critical to improving shrimp quality and production efficiency. This paper proposes an Evolution COnstructed (ECO) features based method to automatically evaluate shrimp shape completeness. Rather than depends on human expert-designed features or deliberated image processing techniques, the proposed method automatically constructs features that are used by AdaBoost model to detect broken shrimp. Experimental results show that ECO features based method obtains a 95.1% overall classification accuracy with a 0.948 precision rate and a 0.920 recall on the 879 shrimp samples collected for testing. Although the experiment was performed on one select species to prove feasibility, the proposed method can be easily adapted to other species. © 2013 Elsevier B.V.

Zhang D.,Sun Yat Sen University | Lee D.-J.,Brigham Young University | Tippetts B.J.,Smart Vision Works, Llc | Lillywhite K.D.,Smart Vision Works, Llc
Journal of Food Engineering | Year: 2014

An efficient histogram analysis algorithm is proposed for real-time automated fruit surface quality evaluation. This approach, based on short-wave infrared imaging, provides excellent image contrast between the fruit surface and delaminated skin, which allows significant simplification of image processing algorithm and reduction of computational power requirements. The proposed method employs a very efficient training procedure to produce a normalized gray scale histogram and its corresponding skin threshold for each quality class. By histogram comparison, the test fruit is assigned to one of the four quality classes and an adaptive threshold is calculated for segmenting skin delamination areas from the fruit surface. The final quality grade is determined according to the fruit size and the percentage of delaminated skin. Experiment was performed in a packing facility in Arizona, USA. Testing results show the proposed method achieves 95-98% grading accuracy for different grades. Although this paper uses Medjool dates as an example to demonstrate the performance of the proposed method, it is suitable for and can be easily adapted to other fruit or vegetable grading applications. The proposed method has been implemented and used for commercial production for date quality evaluation. © 2014 Elsevier Ltd. All rights reserved.

Discover hidden collaborations