DAViS Camera Optical Flow

Almatrafi, Mohammed; Hirakawa, Keigo

doi:10.1109/tci.2019.2948787

Cited by 20 publications

(20 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, the method in [46] exploits the high spatial fidelity of APS and temporal fidelity of DVS to compute spatial temporal derivatives for hybrid hardware called DAViS [47]. Benchmarking datasets for DVS-based optical flow and real-time performance evaluation platform have helped accelerate the progress of research in optical flow for neuromorphic cameras [33], [43], [46].…”

Section: Dynamic Vision Sensor (Dvs)mentioning

confidence: 99%

“…The existing benchmarking datasets have played a critical role in the progress of research in optical flow for neuromorphic cameras [33], [43], [46]. However, they are not without shortcomings.…”

Section: Dvsmotion20 Datasetmentioning

confidence: 99%

“…The dataset in [43] update ground truth motion at 20Hz sampling rate-slow considering that DVS is accurate to microseconds. The spatial resolution of sequences in [46] is small. Therefore, we collected a new dataset-called DVSMOTION20-using IniVation DAViS346 camera in attempt to further enhance the progress of DVS-based optical flow methods.…”

Section: Dvsmotion20 Datasetmentioning

confidence: 99%

“…We used a standard checkerboard calibration target to recover the intrinsic parameters of the camera. We infer ground truth pixel velocity stemming from camera motion using the inertial measurement unit (IMU), similar to prior benchmarkings in [33], [46]. Specifically, we placed the camera on a gimbal as shown in Figure 8, restricting the movement to yaw, pitch, and roll rotations (i.e.…”

Section: Dvsmotion20 Datasetmentioning

confidence: 99%

“…We also compared to the state-of-the-art DAVIS optical flow method DAVIS-OF [46]. Because this method makes use of DVS (events, high temporal fidelity) as well as APS (intensity, high spatial fidelity) data, we expect it to perform better than the DVSonly methods.…”

Section: Setup and Comparisonsmentioning

confidence: 99%

See 4 more Smart Citations

Distance Surface for Event-Based Optical Flow

Almatrafi

Baldwin

Aizawa

et al. 2020

IEEE Trans. Pattern Anal. Mach. Intell.

Self Cite

View full text Add to dashboard Cite

We propose DistSurf-OF, a novel optical flow method for neuromorphic cameras. Neuromorphic cameras (or event detection cameras) are an emerging sensor modality that makes use of dynamic vision sensors (DVS) to report asynchronously the log-intensity changes (called "events") exceeding a predefined threshold at each pixel. In absence of the intensity value at each pixel location, we introduce a notion of "distance surface"-the distance transform computed from the detected events-as a proxy for object texture. The distance surface is then used as an input to the intensity-based optical flow methods to recover the two dimensional pixel motion. Real sensor experiments verify that the proposed DistSurf-OF accurately estimates the angle and speed of each events.

show abstract

Section: Dynamic Vision Sensor (Dvs)mentioning

confidence: 99%

Section: Dvsmotion20 Datasetmentioning

confidence: 99%

Section: Dvsmotion20 Datasetmentioning

confidence: 99%

Section: Dvsmotion20 Datasetmentioning

confidence: 99%

Section: Setup and Comparisonsmentioning

confidence: 99%

See 3 more Smart Citations

Distance Surface for Event-Based Optical Flow

Almatrafi

Baldwin

Aizawa

et al. 2020

IEEE Trans. Pattern Anal. Mach. Intell.

Self Cite

View full text Add to dashboard Cite

show abstract

Event Enhanced High-Quality Image Recovery

Wang

et al. 2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Object Tracking with a Fusion of Event-Based Camera and Frame-Based Camera

Sun

Frémont

2022

Lecture Notes in Networks and Systems

View full text Add to dashboard Cite

The framed-based camera is commonly used for object tracking tasks. However, under poor light conditions, the frame camera cannot work properly and provide stable detection for the tracking system. Also, it has motion blur when the object is moving fast. Compared to the frame-based camera, the event camera has a higher temporal resolution and dynamic range. The event data is transmitted immediately when the brightness of each pixel changes. The higher temporal resolution helps the event camera avoid the motion blur and provide more precise temporal information. Moreover, the higher dynamic range allows the event camera to work in extreme light conditions, such as evening, raining, and strong sunshine environments. In all, those advantages make the event cameras an applicable complementary sensor to the frame cameras. In this paper, several optical flow algorithms for the event data are tested. Then, a clustering algorithm is proposed to generate the detection and hybrid it with the detection from frame images. At last, the PMBM filter is used to realize object tracking and test it on our self-recorded dataset with the DAVIS346 and several publicly available datasets.

show abstract

DAViS Camera Optical Flow

Cited by 20 publications

References 46 publications

Distance Surface for Event-Based Optical Flow

Distance Surface for Event-Based Optical Flow

Event Enhanced High-Quality Image Recovery

Object Tracking with a Fusion of Event-Based Camera and Frame-Based Camera

Contact Info

Product

Resources

About