University System of Maryland

California Strawberry Commission

Industry Vision Automation Corp.

Yang Tao

Gary E Seibel

Xin Chen

Dongyi Wang

John Lin

Robert Vinson

Maxwell Holmes

Anjana Hevaganinge

Mohamed Amr Ali

Chiao-Yi Wang

Xuemei Cheng

Hansong Jing

Bin Zhu

Fenghua Jin

A non-contact system for the sensing the concentration of a compound includes a hyperspectral imaging device configured to capture a hyperspectral image of a fluid, a flow cell configured to enable the capturing of a hyperspectral image of a fluid, a process, and a memory. The memory includes instructions stored thereon which, when executed by the processor, cause the system to generate a hyperspectral image of the fluid in the flow cell, generate several spectral signals based on the hyperspectral image, provide the spectral signal as an input to a machine learning network, and predict by the machine learning network the concentration of a compound in a fluid.

Systems and methods for compound concentration sensing in fluids

A non-contact system for the sensing of pH includes a hyperspectral imaging device configured to capture a hyperspectral image of a fluid, a flow cell configured to enable the capturing of a hyperspectral image of a fluid, a process, and a memory. The memory includes instructions stored thereon, which, when executed by the processor, cause the system to generate a hyperspectral image of the fluid in the flow cell, generate several spectral signals based on the hyperspectral image, provide the spectral signal as an input to a machine learning network, and predict by the machine learning network a pH of a fluid.

Systems and methods for pH sensing in fluids

An automated method for crab meat picking which has an image processing system configured with an imaging sub-system and an image processing sub-system acting in cooperation with each other where the image processing system operates in accordance with a processing routine. An image of a crab to be processed is obtained by the imaging sub-system which is transmitted to the image processing system where the processing routine determines appropriate cut lines to be made on the crab being processed based on instructions from the image processing sub-system. The crab being processed is then cut in accordance with the appropriate cutting lines developed.

Automated crab meat picking method

A system and methods are provided for removal of undesired portions of a fruit or vegetable, such as removal of calyxes from strawberries before they are flash frozen. An automated process for high-throughput fruit or vegetable calyx removal includes a loading system, an identification system, and a removal system. The loading system is configured to transport the fruit or vegetable through the automated process. The loading system may also orient the fruits or vegetables along an axis of the fruit and or align the fruit or vegetables in a desired pattern, orientation, and/or arrangement. The identification system is configured to locate the calyx and determines calyx position data and an optimal cutting path for individual fruit. The removal system uses data received from the identification system to separate the calyx from the fruit or vegetable.

Automated fruit and vegetable calyx or stem removal machine

Intelligence guided system and method for fruits and vegetables processing includes a conveyor for carrying produces, various image acquiring and processing hardware and software, water and air jets for cutting and controlling the position and orientation of the produces, and a networking hardware and software, operating in synchronism in an efficient manner to attain speed and accuracy of the produce cutting and high yield and low waste produces processing. The 2nd generation strawberry decalyxing system (AVID2) uniquely utilizes a convolutional neural network (AVIDnet) supporting a discrimination network decision, specifically, on whether a strawberry is to be cut or rejected, and computing a multi-point cutline curvature to be cut along by rapid robotic cutting tool.

Automatic vision guided intelligent fruits and vegetables processing system and method

A vision guided intelligent system for automated crab meat picking operates in a fully automated or semi-automatic modes of operation using a crab meat picking routine based on (a) the CNN model localization of back-fin knuckles algorithm, and/or (b) the Deep Learning model which accurately locates not only knuckle positions, but also crab legs and crab cores, with a high pixel accuracy (up to 0.9843), and low computation time. The subject system uses a concept of analyzing crab morphologies obtained from digital crab images, and, using a Deep Learning architecture integrated in the system, segments crab images into five regions of interest in a single step with high accuracy and efficiency. The image segmentation results are used for generating crab cut lines in XYZ and angular directions, determining starting cutting points in Z plane, and guiding cutting tools and end effectors to automatically cut crabs and harvest crab meat.

Automated crab meat picking system and method

A process for automated high-throughput fruit or vegetable calyx removal includes a material handling system, a vision system, and a cutting system. The material handling system is capable of transporting the fruit or vegetable through the automated process. The material handling system may also orient the fruits or vegetables along an axis of the fruit and or align the fruit or vegetables in a desired pattern, orientation, and/or configuration. The vision system identifies the calyx and determines calyx position data and optimal cutting angle for individual fruit. The cutting system uses data received from the vision system to automatically remove the calyx from the fruit or vegetables.

A combined X-ray and laser 3D imaging system for food safety inspection, which uses a 3D laser subsystem to get accurate depth information, which is further combined with an x-ray image to achieve accurate physical contamination detection in poultry and other meat products. A unique calibration model is used to calibrate the x-ray and laser 3D imaging systems at the same time. And a nested multi-thread software structure is implemented to prevent data conflict and ensure fully use of system resources during the physical contamination detection of the poultry and other meat products.

Growing community of inventors

North Potomac, MD, United States of America

Yang Tao