### Run SurfRCaT Application

Source: https://conlin-matt.github.io/SurfRCaT/download.html

Execute this command to launch the SurfRCaT application after all dependencies have been installed and the correct directory is active. This command is used to invoke the tool.

```bash
fbs run
```

--------------------------------

### Install Python Packages with Pip

Source: https://conlin-matt.github.io/SurfRCaT/download.html

Install additional Python packages required for the GUI and data processing after activating the Conda environment. These packages include fbs, pptk, and reverse_geocoder.

```bash
pip install fbs pptk reverse_geocoder
```

--------------------------------

### Create and Activate Conda Environment

Source: https://conlin-matt.github.io/SurfRCaT/download.html

Use these commands to create a new Conda environment named 'SurfRCaT_env' with specified Python version and packages, then activate it. Ensure Anaconda is installed and accessible via the prompt.

```bash
conda config --set channel_priority strict
conda create -n SurfRCaT_env -c conda-forge python=3.6 python-pdal pyqt numpy pandas matplotlib opencv requests pyshp utm lxml
conda activate SurfRCaT_env
```

--------------------------------

### Navigate to Project Directory

Source: https://conlin-matt.github.io/SurfRCaT/download.html

Change the current directory to the location where the SurfRCaT repository has been cloned or downloaded. Replace '<your directory>' with the actual path.

```bash
cd <your directory>\SurfRCaT-master
```

--------------------------------

### Import Rectified Products into Python

Source: https://conlin-matt.github.io/SurfRCaT/extensions.html

Load a .pkl rectified image file using the pickle module.

```python
import pickle

f = open('<path_to_image>/<im>_rectif.pkl','rb')
frameRect = pickle.load(f)
```

--------------------------------

### Download Airborne Lidar Datasets

Source: https://conlin-matt.github.io/SurfRCaT/extensions.html

Automate the discovery, filtering, and downloading of coastal lidar datasets based on geographic coordinates.

```python
import SurfRCaT
import ftplib
import numpy as np

camera_latitude = <input latitude (WGS84) here>
camera_longitude = <input longitude (WGS84) here>

# Get the IDs of datasets that are near this location (same state and/or coast) #
closeIDs = SurfRCaT.getLidar_FindPossibleIDs(camera_latitude,camera_longitude)

# Search these close datasets to find those that cover this location #
ftp = ftplib.FTP('ftp.coast.noaa.gov',timeout=1000000)
ftp.login('anonymous','anonymous')
ftp.cwd('/pub/DigitalCoast')
dirs = [i for i in ftp.nlst() if 'lidar' in i]
alldirs = []
for ii in dirs:
    ftp.cwd(ii)
    alldirs.append([ii+'/'+i for i in ftp.nlst() if 'geoid' in i])
    ftp.cwd('../')  

appropID = list() # Initiate list of IDs that contain the camera location #
i = 0
for ID in IDs:  
i = i+=1
    check = SurfRCaT.getLidar_TryID(ftp,alldirs,ID,camera_latitude,camera_longitude)
    ftp.cwd('../../../../')

    if check:
        if len(check)>0:       
            appropID.append(ID)

# Choose a dataset #
IDToDownload = appropID[<Choose which dataset you want>]

# Determine the tiles that are close enough to the camera to download #
sf = SurfRCaT.getLidar_GetShapefile(IDToDownload)
poly = SurfRCaT.getLidar_CalcViewArea(30,20,1000,camera_latitude,camera_longitude)
        
tilesKeep = list()
for shapeNum in range(0,len(sf)):
    out = SurfRCaT.getLidar_SearchTiles(sf,poly,shapeNum,camera_latitude,camera_longitude)
    if out:
        tilesKeep.append(out)

# Download the portion of the dataset close to the camera #
lidarDat = np.empty([0,3])
for thisFile in tilesKeep:
    lidarXYZsmall = SurfRCaT.getLidar_Download(thisFile,IDToDownload,camera_latitude,camera_longitude)
    lidarDat = np.append(lidarDat,lidarXYZsmall,axis=0)

# Format the point cloud as a Pandas DataFrame (coordinates relative to input location) #
pc = SurfRCaT.getLidar_CreatePC(lidarDat,camera_latitude,camera_longitude)
```

--------------------------------

### Import Rectified Products into Matlab

Source: https://conlin-matt.github.io/SurfRCaT/extensions.html

Load a .mat rectified image file and structure it into a frameRect struct compatible with CIRN routines.

```matlab
load('<path_to_image>/<im>_rectif.mat');
frameRect.x = x; frameRect.y = y; frameRect.I = I;
```

--------------------------------

### Extract Video Frames Programmatically

Source: https://conlin-matt.github.io/SurfRCaT/extensions.html

Use SurfRCaT to extract frames from a video file at a specified rate.

```python
import SurfRCaT
import cv2
	
vid = 'C:/path/to/video.mp4'
saveDir = 'C:/directory/to/save/frames/to'

cap = cv2.VideoCapture(vid)
numFrames = int(cap.get(7))
fps = cap.get(5)
vidLen = int(numFrames/fps)

secondsPerFrame = 1 # Leave as 1 to ignore this parameter #
rate = 2 # 2 frames/second #

SurfRCaT.getImagery_GetStills(vid,secondsPerFrame,rate,vidLen,saveDir)
```

=== COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.