|
7 | 7 | [](https://crates.io/crates/adder-codec-rs) |
8 | 8 |
|
9 | 9 | A unified framework for event-based video. Encoder/transcoder/decoder for ADΔER (Address, Decimation, Δt Event |
10 | | -Representation) video streams. Includes a transcoder for casting framed video into an ADΔER representation in a manner |
11 | | -which preserves the temporal synchronicity of the source, but enables many-frame intensity averaging on a per-pixel |
| 10 | +Representation) video streams. Includes a transcoder for casting framed video and event camera video into an ADΔER representation in a manner |
| 11 | +which preserves the temporal synchronicity of the source, but enables long-term intensity averaging on a per-pixel |
12 | 12 | basis and extremely high dynamic range. |
13 | 13 |
|
14 | 14 |  |
15 | 15 |
|
16 | | -## _adder-viz_ |
17 | | -The easiest way to get up and running with ADΔER is with the GUI program, _adder-viz_. This allows you to experiment in real time with the various transcoder settings described in our papers (below). |
18 | | - |
19 | | -First, you need to get the necessary dependencies installed. These instructions assume you're running a flavor of Debian Linux. It should also work within the Windows Subsystem for Linux, which now supports graphical display. |
20 | | - |
21 | | -If you don't want to install these dependencies, you can use the VirtualBox image provided [here](https://drive.google.com/drive/folders/1pCpvvyvwT3sb6fkV4uwePpP7mQN5o-sL?usp=sharing). The link provides instructions for running the virtual machine. |
22 | | - |
23 | | -### Install Rust |
24 | | - |
25 | | -Use the official instructions [here](https://www.rust-lang.org/tools/install) to install Rust. |
26 | | - |
27 | | -### Dependencies |
28 | | - |
29 | | -Audio/Video |
30 | | -``` |
31 | | -sudo apt-get install -y --fix-missing libodbccr2 libodbc2 libssl-dev alsa-utils libasound2-dev portaudio19-dev build-essential libpulse-dev libdbus-1-dev libudev-dev libatk1.0-dev libgtk-3-dev libavfilter-dev libavdevice-dev ffmpeg |
32 | | -``` |
33 | | - |
34 | | -Clang |
35 | | -``` |
36 | | -sudo bash -c "$(wget -O - https://apt.llvm.org/llvm.sh)" |
37 | | -``` |
38 | | - |
39 | | -Other |
40 | | -``` |
41 | | -sudo apt-get install -y portaudio19-dev build-essential libpulse-dev libdbus-1-dev pkg-config libx11-dev libatk1.0-dev libgtk-3-dev libxcb-render0-dev libxcb-shape0-dev libxcb-xfixes0-dev libwayland-dev libxkbcommon-dev libopencv-dev |
42 | | -``` |
43 | | - |
44 | | -### Install _adder-viz_ |
45 | | - |
46 | | -To enable the use of _source-modeled lossy compression_ (the only such scheme for event-based video, as far as I'm |
47 | | -aware), install with the `compression` feature enabled: |
48 | | - |
49 | | -``` |
50 | | -cargo install adder-viz -F "compression" |
51 | | -``` |
52 | | - |
53 | | -To transcode from an iniVation DVS/DAVIS camera (using an older method, not yet unified with the Prophesee transcoder), |
54 | | -enable the `open-cv` feature: |
55 | 16 |
|
56 | | -``` |
57 | | -cargo install adder-viz -F "compression open-cv" |
58 | | -``` |
| 17 | +Source 8-bit image frame with shadows boosted ([source video](https://www.pexels.com/video/river-between-trees-2126081/)) | Frame reconstructed from ADΔER events, generated from 48 input frames, with shadows boosted. Note the greater dynamic range and temporal denoising in the shadows. |
| 18 | +:-------------------------:|:-------------------------: |
| 19 | + |  |
59 | 20 |
|
60 | | -### Running |
| 21 | +## _adder-viz_ |
| 22 | +The easiest way to get up and running with ADΔER is with the GUI program, _adder-viz_. Folow the instructions [here](https://github.com/ac-freeman/adder-codec-rs/tree/main/adder-viz). |
| 23 | + |
| 24 | +## System model |
61 | 25 |
|
62 | | -Simply enter `adder-viz` in your terminal. |
| 26 | +Click the image to view the full system model conveyed by this software. I compare the ADΔER approach to traditional framed and event camera systems. |
63 | 27 |
|
| 28 | + |
64 | 29 |
|
65 | | -Source 8-bit image frame with shadows boosted ([source video](https://www.pexels.com/video/river-between-trees-2126081/)) | Frame reconstructed from ADΔER events, generated from 48 input frames, with shadows boosted. Note the greater dynamic range and temporal denoising in the shadows. |
66 | | -:-------------------------:|:-------------------------: |
67 | | - |  |
68 | 30 |
|
69 | 31 | ## Included crates |
70 | 32 |
|
|
0 commit comments