The PASCAL Visual Object Classes Challenge

Обнаружение транспортных средств на изображениях загородных шоссе на основе метода Single shot multibox Detector

/pdf/deep-learning-in-medical-image-analysis-ilst8as5f9.pdf

Deep Learning in Medical Image Analysis

This chapter presents a summary of the issues discussed during the one day workshop on “Support Vector Machines (SVM) Theory and Applications” organized as part of the Advanced Course on Artificial Intelligence (ACAI ’99) in Chania, Greece [19]. The goal of the chapter is twofold: to present an overview of the background theory and current understanding of SVM, and to discuss the papers presented as well as the issues that arose during the workshop.

Support vector machines: Theory and applications

In the last decade, Human Activity Recognition (HAR) has become a vibrant research area, especially due to the spread of electronic devices such as smartphones, smartwatches and video cameras present in our daily lives. In addition, the advance of deep learning and other machine learning algorithms has allowed researchers to use HAR in various domains including sports, health and well-being applications. For example, HAR is considered as one of the most promising assistive technology tools to support elderly’s daily life by monitoring their cognitive and physical function through daily activities. This survey focuses on critical role of machine learning in developing HAR applications based on inertial sensors in conjunction with physiological and environmental sensors.

Human Activity Recognition Using Inertial, Physiological and Environmental Sensors: A Comprehensive Survey

Fetoscopic laser photocoagulation is a minimally invasive procedure to treat twin-to-twin transfusion syndrome during pregnancy by stopping irregular blood flow in the placenta. Building an image mosaic of the placenta and its network of vessels could assist surgeons to navigate in the challenging fetoscopic environment during the procedure.We propose a fetoscopic mosaicking approach by combining deep learning-based optical flow with robust estimation for filtering inconsistent motions that occurs due to floating particles and specularities. While the current state of the art for fetoscopic mosaicking relies on clearly visible vessels for registration, our approach overcomes this limitation by considering the motion of all consistent pixels within consecutive frames. We also overcome the challenges in applying off-the-shelf optical flow to fetoscopic mosaicking through the use of robust estimation and local refinement.We compare our proposed method against the state-of-the-art vessel-based and optical flow-based image registration methods, and robust estimation alternatives. We also compare our proposed pipeline using different optical flow and robust estimation alternatives.Through analysis of our results, we show that our method outperforms both the vessel-based state of the art and LK, noticeably when vessels are either poorly visible or too thin to be reliably identified. Our approach is thus able to build consistent placental vessel mosaics in challenging cases where currently available alternatives fail. 

/pdf/robust-fetoscopic-mosaicking-from-deep-learned-flow-fields-1fjjao2c.pdf

Robust fetoscopic mosaicking from deep learned flow fields

Determining the externally-induced motion of a soft robot in minimally-invasive procedures is highly challenging and commonly demands specific tools and dedicated sensors. Intrinsic force sensing paired with a model describing the robot's compliance offers an alternative pathway which relies heavily on knowledge of the characteristic mechanical behaviour of the investigated system. In this work, we apply quasi-static intrinsic force sensing to a miniature, parallel soft robot designed for endoluminal ear interventions. We characterize the soft robot's nonlinear mechanical behaviour and devise methods for inferring forces applied to the actuators of the robot from fluid pressure and volume information of the working fluid. We demonstrate that it is possible to detect the presence of an external contact acting on the soft robot's actuators, infer the applied reaction force with an accuracy of 28.1 mN and extrapolate from individual actuator force sensing to determining forces acting on the combined parallel soft robot when it is deployed in a lumen, which can be achieved with an accuracy of 75.45 mN for external forces and 0.47 Nmm for external torques. The intrinsically-sensed external forces can be employed to estimate the induced motion of the soft robot in response to these forces with an accuracy of 0.11 mm in translation and 2.47$^\circ$ in rotational deflection. The derived methodologies could enable designs for more perceptive endoscopic systems and pave the way for developing sensing and control strategies in endoluminal and transluminal soft robots.

/pdf/intrinsic-force-sensing-for-motion-estimation-in-a-parallel-3vqqcixt.pdf

Intrinsic Force Sensing for Motion Estimation in a Parallel, Fluidic Soft Robot for Endoluminal Interventions

This paper summarizes the design and fabrication of a four degree of freedom autonomous robotic arm using Digital image processing. The robotic arm boasts a high performance, RISC architecture based microcontroller manufactured by Atmel, the AtMega16. Control of the robotic arm has been achieved successfully using four servo motors, each of which incorporates high resolution quadrature encoders. The robotic arm is equipped with a pair of high resolution digital cameras. These cameras transmit real time video to a Pentium based processor. The image processing module searches the video stream for predefined templates and calculates the coordinates of the object to grasp and transmits them serially to the microcontroller. The microcontroller implements inverse kinematics algorithms and then actuates the respective motors through angles so as to reach the coordinates desired in the most efficient manner. The motors are actuated using the internal PWM channels of the microcontroller and power amplifiers using efficient Mosfets. The robotic arm also has the provision of being controlled without the cameras relying on user input for the starting and terminating points. These coordinates are fed to the controller directly using a keypad and LCD module eliminating the Pentium processor. Thus even without a vision system the robotic arm may be defined as being autonomous. The end effector is a two finger gripper. The robotic arm has a load bearing capacity of upto 500gms and a maximum workspace of about 650mm of a meter.

/pdf/fabrication-and-control-of-4-dof-autonomous-robotic-arm-3y2k9s9n9j.pdf

Fabrication and Control of 4-DOF, Autonomous Robotic Arm Using Low Cost AVR Controller

Multisensor perfusion assessment cohort study: Preliminary evidence toward a standardized assessment of indocyanine green fluorescence in colorectal surgery.

We propose a gyro-based camera-motion detection method for videos captured with smartphones. First, the delay between the acquisition of video and gyroscope data is estimated using similarities induced by camera motion in the two sensor modalities. Pan, tilt and shake are then detected using the dominant motions and high frequencies in the gyroscope data. Morphological operations are applied to remove outliers and to identify segments with continuous camera-motion. We compare the proposed method with existing methods that use visual or inertial sensor data.

http://www.eecs.qmul.ac.uk/~andrea/papers/2015_ACMMultimedia_GyroBasedCameraMotionDetection_Bano_Cavallaro_Parra.pdf

Sophia Bano

Papers

Robust fetoscopic mosaicking from deep learned flow fields

Intrinsic Force Sensing for Motion Estimation in a Parallel, Fluidic Soft Robot for Endoluminal Interventions

Fabrication and Control of 4-DOF, Autonomous Robotic Arm Using Low Cost AVR Controller

Multisensor perfusion assessment cohort study: Preliminary evidence toward a standardized assessment of indocyanine green fluorescence in colorectal surgery.

Gyro-based Camera-motion Detection in User-generated Videos