Real time edge inference monitoring with rt-ai Edge

rt-ai Edge is progressing nicely and now supports multi-node operation (i.e. multiple networked servers participating in a processing network) along with real-time monitoring. The screen capture shows a simple processing network where the video feed from a camera is passed through a DeepLab-v3+ stream processing element (SPE) and then on to two separate media viewers. At the top of each SPE block in the Designer window is some text like Cam(Default). Here, Cam is the name given to the SPE while Default is the name of the node (server) on which the SPE is running. In this design there are two nodes, Default and rtai0.

The code underlying the common SPE API communicates with the Designer window and supplies the stats about bytes and messages in and out. Soon, this path will also allow SPE-specific real-time parameter tweaking from the Designer window.

To add a node to the system, it just needs to have all of the prerequisites installed and run a special NodeManager SPE. This also communicates with the Designer and supports SPE deployment and runtime control, activated when the user presses the Deploy design button. Moving an SPE between nodes is just a case of reassigning it, generating the design and then deploying the design again.

The green outlines around each SPE indicate the state of the SPE and the node on which it is running. When it is all green, as in the first screen capture, this indicates that both SPE and node are running. For the second screen capture, I manually terminated the View2 SPE on rtai0. The inner part of the outline has now gone red. This indicates that the node is up but the SPE is down. If the outline is all red, it means that the node is down and not communicating with the Designer.

It’s interesting to note that DeepLab-v3+ is processing around 5 frames per second using a GTX-1080 GPU. The input rate from the camera is 30 frames per second. The processor drops frames while it is still processing an earlier frame, ensuring that queues do not build up and latency is kept to a minimum.

DeepLabv3+ Stream Processing Element (SPE) for rt-ai Edge

Integrating DeepLabv3+ with rt-ai Edge turned out to be pretty straightforward and follows from an existing TensorFlow-based Inception Stream Processing Element (SPE). The screen capture above shows an example of what it can do when given a video stream, where the DeepLab SPE has removed all pixels that aren’t part of recognized objects. This is why I am waving a bottle of beer about (and not because it is after 5pm). The PASCAL VOC dataset on which the model I am using has been trained can recognize a finite set of categories of objects. Waving a cow about didn’t seem practical hence the bottle. This is the original frame from the camera:

The DeepLab SPE also allows a specific category to be selected. In the case of the capture below, this was just the bottle:

On the right hand side of the media viewer screen you can see the metadata that has been generated by the DeepLab SPE. This is an example of how rt-ai Edge SPEs can be used to enhance the semantic content of data – video frames in this case.

It is pretty easy to configure the DeepLab SPE using rtaiDesigner:

This is the design screen showing the fairly trivial flow used for this test. Cam is a webcam capture SPE, Audio is an audio capture SPE. The DeepLab SPE is connected in the flow between the capture SPE and the media view SPE.

An interesting feature of rt-ai Edge is how SPEs can be configured. An SPE consists of some code (Python scripts in these cases) and a module spec (mspec) file. The mspec file contains information about subscriber and publisher ports as well as a section that is used to generate a configuration dialog. An example for the DeepLab SPE module dialog is shown above. This is the mspec file that generated it:

{
    "ModuleType" : "DeepLab",

    "ModuleDialog" : {
        "DialogName" : "DeepLab",
        "DialogDesc" : "Settings dialog for DeepLab semantic segmentation",

        "DialogData" : [
            {
                "VarName" : "OutputFormat",
                "VarDesc" : "Output frame format",
                "VarType" : "ConfigSelection",
                "VarValue" : "0",
                "VarStringArray" : [{ "VarEntry" : "Color map"},{"VarEntry" : "Masked image" },{"VarEntry" : "Single category masked image" }]
            },
            {
                "VarName" : "Category",
                "VarDesc" : "Single category selector",
                "VarType" : "ConfigSelection",
                "VarValue" : "15",
                "VarStringArray" : [
                    {"VarEntry" : "background"},
                    {"VarEntry" : "aeroplane"},
                    {"VarEntry" : "bicycle" },
                    {"VarEntry" : "bird" },
                    {"VarEntry" : "boat" },
                    {"VarEntry" : "bottle" },
                    {"VarEntry" : "bus" },
                    {"VarEntry" : "car" },
                    {"VarEntry" : "cat" },
                    {"VarEntry" : "chair" },
                    {"VarEntry" : "cow" },
                    {"VarEntry" : "diningtable" },
                    {"VarEntry" : "dog" },
                    {"VarEntry" : "horse" },
                    {"VarEntry" : "motorbike" },
                    {"VarEntry" : "person" },
                    {"VarEntry" : "pottedplant" },
                    {"VarEntry" : "sheep" },
                    {"VarEntry" : "sofa" },
                    {"VarEntry" : "train" },
                    {"VarEntry" : "tv" }
                ]
            },
            {
                "VarName" : "Preview",
                "VarDesc" : "Enable preview",
                "VarType" : "ConfigBool",
                "VarValue" : "false"
            }
        ]
    },
    
    "ModulePubSubs" : {
        "Pubs" : {
            "VideoOut" : "VideoMJPEG"
        },

        "Subs" : {
            "VideoIn" : "VideoMJPEG"
        }
    }
}

This makes it very easy to try out different settings. Use the module’s dialog to change something, regenerate the design using the Generate design button and then restart the network. Right now, for testing, rtaiDesigner generates start.sh and stop.sh scripts that can be used to quickly implement changes. Hopefully, in the future, configuration changes will be possible on the fly without having to restart the stream processing network.

Samsung 360 Round – 360 degree 3D live streaming

The problem with the traditional technique of texturing the inside of a sphere with a 360 equirectangular image or video to form a background in a virtual scene is that it looks like a painting of reality when viewed in a VR headset. What’s missing is a sense of depth. The Samsung 360 Round looks like it could solve that problem by live streaming a 3D 360 feed with 4096 x 2048 resolution per eye. Hopefully this would mean that the background would merge better with virtual objects in the foreground.

The downside is the cost ($10,500!) and the PC requirements for live streaming – a couple of GTX 1080 Tis (total about $1500) and an i7-6950X CPU (around $1500) makes for a pretty expensive setup. And I am not sure if I understand this correctly but you might need two PCs with that setup. Yikes.

Using the Garmin VIRB 360 HDMI port

The micro-HDMI cables turned up so I was finally able to try out the Garmin VIRB 360 HDMI port. The photo above shows the result although it is a photo from the screen of a 4k monitor and there is a bit of reflection – the real quality is much better than this. The stitching really isn’t noticeable in this 3840 x 2160 video sample and it seems like the HDMI output is going to be perfect for my projects. The VIRB Mobile app makes it pretty easy to set up and control the camera which is very handy.

One thing that is noticeable unless the camera is modified is the door that covers the HDMI port!

Without this high tech modification, the spring on the door ensures that the door is in the frame.

Another thing that is a shame is that you cannot connect a USB cable to power the camera at the same time as an HDMI cable. However, Garmin do have a powered tripod mount that would solve this problem. I guess there is going to be one of those in my future. Also in my future is a different tripod system so you can’t see it as clearly as in the first photo!

Next step is to get it working with the Blackmagic video capture card.

Latest fun thing in the office: a Garmin VIRB 360 camera

360 degree video is all the rage right now so I cannot be left behind! One of the things I like about the Garmin VIRB 360 is the in-camera stitching and very high resolution. It is also incredibly small. Judging by my photo though keeping the dust off will be a challenge :-).

Typically I forgot to order a micro-HDMI cable so I can’t test live capture to a PC but I can create videos on the SD card. Great fun!

Cable will turn up tomorrow with any luck. I am eager to see how usable the HDMI is for live 360 videos.

HoloLens Spectator View…without the HoloLens


I’ll explain the photo above in a moment. Microsoft’s Spectator View is a great device but not that practical in the general case. For example, the original requires modifications to the HoloLens itself and a fairly costly camera capable of outputting clean 1080p, 2k or 4k video on an HDMI port. Total cost can be more than $6000 depending on the camera used. My goal is to do much the same thing but without requiring a HoloLens and at a much lower cost – just using a standard camera with fairly simple calibration. Not only that, but I want to stream the mixed reality video across the internet using WebRTC for both conventional and stereo headsets (such as VR headsets).

So, why is there a HoloLens in the photo? This is the calibration setup. The camera that I am using for this Mixed Reality streaming system is a Stereolabs ZED. I have been working with this quite a bit lately and it seems to work extremely well. Notably it can produce a 2K stereo 3D output, a depth map and a 6 DoF pose, all available via a USB 3 interface and a very easy to use SDK.

Unlike Spectator View, the Unity Editor is not used on the desktop. Instead, a standard HoloLens UWP app is run on a Windows 10 desktop, along with a separate capture, compositor and WebRTC streamer program. There is some special code in the HoloLens app that talks to the rest of the streaming system. This can be present in the HoloLens app even when run on the HoloLens without problems (it just remains inactive in this case).

The calibration process determines, amongst other things, the actual field of view of the ZED and its orientation and position in the Unity scene used to create the virtual part of the mixed reality scene. This is essential in order to correctly render the virtual scene in a form that can be composited with the video coming from the ZED. This is why the HoloLens is placed in this prototype rig in the photo. It puts the HoloLens camera roughly in the same vertical plane as the ZED camera with a small (known) vertical offset. It’s not critical to get the orientation exactly right when fitting the HoloLens to the rig – this can be calibrated out very easily. The important thing is that the cameras see roughly the same field. That’s the because the next step matches features in each view and, from the positions of the matches, can derive the field of view of the ZED and its pose offset from the HoloLens. This then makes it possible to set the Unity camera in the desktop in exactly the right position and orientation so that the scene it streams is correctly composed.

Once the calibration step has completed, the HoloLens can be removed and used as required. The prototype version looks very ungainly like this! The real version will have a nice 3D printed bracket system that will also have the advantage of reducing the vertical separation and limit the possible offsets.

In operation, it is required that the HoloLens apps running on both the HoloLens(es) and the desktop are sharing data about the Unity scene that allows each device to compute exactly the same scene. In this way, everyone sees the same thing. I am actually using Arvizio‘s own sharing system but any sharing system could be used. The Unity scene generated on the desktop is then composited with the ZED camera’s video feed and streamed over WebRTC. The nice thing about using WebRTC is that almost anyone with a Chrome or Firefox browser can display the mixed reality stream without having to install any plugins or extensions. It is also worth mentioning that the ZED does not have to remain fixed in place after calibration. Because it is able to measure its pose with respect to its surroundings, the ZED could potentially pan, tilt and dolly if that is required.

facerec – adding OpenFace’s face recognition capability to an rtndf data flow pipeline

FaceRecI had obtained some very nice results with OpenFace in a previous project and thought it would be fun to wrap it into an rtndf pipeline processing element (PPE). It’s also a good test to see whether docker containers can be used with rtndf. Turns out they work just fine. OpenFace has some complex dependencies and it is much easier just to pull a docker container than build it locally. One approach would have been to build a new container based on the original bamos/openface but instead facerec uses a bit of a hack involving host directory mapping.

To make it easy to use, there’s a bash script in the rtndf/facerec directory called facerecstart that takes care of the docker command line (which is a bit messy). Of course, in order to recognize faces, the system needs to have been trained. rtndf/facerec includes a modified version of the OpenFace web demo that saves the data from the training in the correct form for facerec. There’s a bash script, trainstart, that starts it going and then a browser and webcam can be used to perform the training.

As with the recognize PPE, facerec can either process the whole frame or just segments that contain motion by using the output from the modet PPE. In fact both recognize and facerec can be used in the same pipeline to get combined recognition:

uvccam -> modet -> facerec -> recognize -> avview

This illustrates one of the nice features of the pipeline concept: metadata and annotation can be added progressively by multiple processing stages, adding significant value to the resulting stream.