This paper presents a novel approach for joint point-feature detection and tracking, designed specifically for Pixel Processor Array (PPA) vision sensors. Instead of standard pixels, PPA sensors consist of thousands of "pixel-processors", enabling massive parallel computation of visual data at the point of light capture. Our approach performs all computation entirely in-pixel, meaning no raw image data need ever leave the sensor for external processing. We introduce a Descriptor-In-Pixel paradigm, in which a feature descriptor is held within the memory of each pixel-processor. The PPA’s architecture enables the response of every processor’s descriptor, upon the current image, to be computed in parallel. This produces a"descriptor response map" which, by generating the correct layout of descriptors across the pixel-processors, can be used for both point-feature detection and tracking. This reduces sensor output to just sparse feature locations and descriptors, read-out via an address-event interface, giving a greater than 1000× reduction in data transfer compared to raw image output. The sparse readout and complete utilization of all pixel-processors makes our approach very efficient. Our implementation upon the SCAMP-7 PPA prototype runs at over 3000 FPS (Frames Per Second), tracking point-features reliably under violent motion. This is the first work performing point-feature detection and tracking entirely in-pixel.1

Abstract This paper presents an agile reactive navigation strategy for driving a non‐holonomic ground vehicle around a pre‐set course of gates in a cluttered environment using a low‐cost processor array sensor. This enables machine vision tasks to be performed directly upon the sensor's image plane, rather than using a separate general‐purpose computer. The authors demonstrate a small ground vehicle running through or avoiding multiple gates at high speed using minimal computational resources. To achieve this, target tracking algorithms are developed for the Pixel Processing Array and captured images are then processed directly on the vision sensor acquiring target information for controlling the ground vehicle. The algorithm can run at up to 2000 fps outdoors and 200 fps at indoor illumination levels. Conducting image processing at the sensor level avoids the bottleneck of image transfer encountered in conventional sensors. The real‐time performance of on‐board image processing and robustness is validated through experiments. Experimental results demonstrate the algorithm's ability to enable a ground vehicle to navigate at an average speed of 2.20 m/s for passing through multiple gates and 3.88 m/s for a ‘slalom’ task in an environment featuring significant visual clutter.

This paper presents a monocular vision based proximity estimation system using abstract features, such as corner points, blobs and edges, as inputs to a neural network. An experimental vehicle was built using a vision system integrating the SCAMP-5 vision chip, a micro-controller, and an RC model car. The vision chip includes image sensor with embedded 256×256 processor SIMD array. The pixel processor array chip was programmed to capture images and run the feature algorithms directly on the focal plane, and then digest them so that only sparse feature description data were read-out in the form of 40 values. By logging the vision output and the output from three infrared proximity sensors, training data were obtained to train three fully connected layer-recurrent neural networks with fewer than 700 parameters each. The trained neural network was able to estimate the proximity to the level of accuracy sufficient for a reactive collision avoidance behaviour to be achieved. The latency of the control system, from image capture to neural network output, was under 4ms, enabling the vehicles to avoid obstacles while moving at 0.64m/s to 1.8m/s in the experiment.

We present a novel method of CNN inference on a pixel processor array device, demonstrating it using a handwritten digit (digits 0-9) classification task, with all steps of the neural network computation performed on the focal plane. The vision chip that we deploy (SCAMP-7) has a 256×256 array of processor elements (PE) integrated within the image sensor. The algorithm runs at over 3000 frames per second (FPS) and over 90% classification accuracy, with the sensor chip only outputting ten scalar values corresponding to the classification scores.

We present a convolutional neural network implementation for pixel processor array (PPA) sensors. PPA hardware consists of a fine-grained array of general-purpose processing elements, each capable of light capture, data storage, program execution, and communication with neighboring elements. This allows images to be stored and manipulated directly at the point of light capture, rather than having to transfer images to external processing hardware. Our CNN approach divides this array up into 4x4 blocks of processing elements, essentially trading-off image resolution for increased local memory capacity per 4x4 ”pixel”. We implement parallel operations for image addition, subtraction and bit-shifting images in this 4x4 block format. Using these components we formulate how to perform ternary weight convolutions upon these images, compactly store results of such convolutions, perform max-pooling, and transfer the resulting sub-sampled data to an attached micro-controller. We train ternary weight filter CNNs for digit recognition and a simple tracking task, and demonstrate inference of these networks upon the SCAMP5 PPA system. This work represents a first step towards embedding neural network processing capability directly onto the focal plane of a sensor.

This paper presents a visual odometry approach using a Pixel Processor Array (PPA) camera, specifically, the SCAMP-5 vision chip. In this device, each pixel is capable of storing data and performing computation, enabling a variety of computer vision tasks to be carried out directly upon the sensor itself. In this work the PPA performs HDR edge detection, perspective correction and image alignment based odometry, allowing the position and heading of a MAV to be tracked at several hundred frames per second. We evaluate our PPA based approach by direct comparison with a motion capture system for a variety of trajectories. These include rapid accelerations that would incur significant motion blur at low frame rates, and lighting conditions that would typically lead to under or over exposure of image detail. Such challenging conditions would often lead to unusable images when relying on traditional image sensors.

We present an approach of estimating constrained egomotion on a Pixel Processor Array (PPA). These devices embed processing and data storage capability into the pixels of the image sensor, allowing for fast and low power parallel computation directly on the image-plane. Rather than the standard visual pipeline whereby whole images are transferred to an external general processing unit, our approach performs all computation upon the PPA itself, with the camera's estimated motion as the only information output. Our approach estimates 3D rotation and a 1D scale-less estimate of translation. We introduce methods of image scaling, rotation and alignment which are performed solely upon the PPA itself and form the basis for conducting motion estimation. We demonstrate the algorithms on a SCAMP-5 vision chip, achieving frame rates >1000Hz at ~2W power consumption.

This paper presents a vision-based control strategy for tracking a ground target using a novel vision sensor featuring a processor for each pixel element. This enables computer vision tasks to be carried out directly on the focal plane in a highly efficient manner rather than using a separate general purpose computer. The strategy enables a small, agile quadrotor Unmanned Air Vehicle (UAV) to track the target from close range using minimal computational effort and with low power consumption. To evaluate the system we target a vehicle driven by chaotic dual-pendulum trajectories. Target proximity and the large, unpredictable accelerations of the vehicle cause challenges for the UAV in keeping it within the downward facing camera's field of view (FoV). A state observer is used to smooth out predictions of the target's location and, importantly, estimate velocity. Experimental results also demonstrate that it is possible to continue to re-acquire and follow the target during short periods of loss in target visibility. The tracking algorithm exploits the parallel nature of the visual sensor, enabling high rate image processing ahead of any communication bottleneck with the UAV controller. With the vision chip carrying out the most intense visual information processing, it is computationally trivial to compute all of the controls for tracking onboard. This work is directed toward visual agile robots that are power efficient and that ferry only useful data around the information and control pathways.

This paper proposes a strategy for transporting a large object to a goal using a large number of mobile robots that are significantly smaller than the object. The robots only push the object at positions where the direct line of sight to the goal is occluded by the object. This strategy is fully decentralized and requires neither explicit communication nor specific manipulation mechanisms. We prove that it can transport any convex object in a planar environment. We implement this strategy on the e-puck robotic platform and present systematic experiments with a group of 20 e-pucks transporting three objects of different shapes. The objects were successfully transported to the goal in 43 out of 45 trials. When using a mobile goal, teleoperated by a human, the object could be navigated through an environment with obstacles. We also tested the strategy in a 3-D environment using physics-based computer simulation. Due to its simplicity, the transport strategy is particularly suited for implementation on microscale robotic systems.

This paper proposes a strategy for transporting a tall, and potentially heavy, object to a goal using a large number of miniature mobile robots. The robots move the object by pushing it. The direction in which the object moves is controlled by the way in which the robots distribute themselves around its perimeter - if the robots dynamically reallocate themselves around the section of the object's perimeter that occludes their view of the goal, the object will eventually be transported to the goal. This strategy is fully distributed, and makes no use of communication between the robots. A controller based on this strategy was implemented on a swarm of 12 physical e-puck robots, and a systematic experiment with 30 randomized trials was performed. The object was successfully transported to the goal in all the trials. On average, the path traced by the object was about 8.4% longer than the shortest possible path.