Files
ItemSense/main.py

109 lines
4.7 KiB
Python

import sys
import cv2
import numpy as np
from PIL import Image
import objc
from AppKit import (
NSApplication, NSApp, NSWindow, NSView, NSImageView, NSButton,
NSStackView, NSImage, NSBitmapImageRep, NSBackingStoreBuffered,
NSWindowStyleMaskTitled, NSWindowStyleMaskClosable,
NSWindowStyleMaskResizable, NSWindowStyleMaskMiniaturizable,
NSTimer, NSMakeSize, NSMakeRect, NSObject, NSLog,
NSUserInterfaceLayoutOrientationVertical, NSLayoutAttributeCenterX,
NSLayoutAttributeCenterY, NSLayoutAttributeWidth, NSLayoutAttributeHeight,
NSLayoutAttributeTop, NSLayoutAttributeBottom, NSLayoutAttributeLeading,
NSLayoutAttributeTrailing
)
from Foundation import NSObject, NSTimer, NSDate
class ItemSenseApp(NSObject):
def applicationDidFinishLaunching_(self, notification):
self.window = NSWindow.alloc().initWithContentRect_styleMask_backing_defer_(
NSMakeRect(0, 0, 800, 600),
NSWindowStyleMaskTitled | NSWindowStyleMaskClosable | NSWindowStyleMaskResizable | NSWindowStyleMaskMiniaturizable,
NSBackingStoreBuffered,
False
)
self.window.setTitle_("ItemSense")
self.window.center()
# Main content view (StackView for layout)
self.stack_view = NSStackView.alloc().init()
self.stack_view.setOrientation_(NSUserInterfaceLayoutOrientationVertical)
self.stack_view.setSpacing_(10)
self.stack_view.setEdgeInsets_((10, 10, 10, 10))
self.window.setContentView_(self.stack_view)
# Image View for Camera Feed
self.image_view = NSImageView.alloc().init()
self.image_view.setImageScaling_(0) # NSImageScaleProportionallyDown
self.stack_view.addView_inGravity_(self.image_view, 1) # Top gravity
# Capture Button
self.capture_button = NSButton.buttonWithTitle_target_action_("Capture", self, "captureClicked:")
self.stack_view.addView_inGravity_(self.capture_button, 3) # Bottom gravity
self.window.makeKeyAndOrderFront_(None)
# Initialize Camera
self.cap = cv2.VideoCapture(0)
if not self.cap.isOpened():
NSLog("Error: Could not open camera")
# Start Timer for 30 FPS
self.timer = NSTimer.scheduledTimerWithTimeInterval_target_selector_userInfo_repeats_(
1.0/30.0, self, "updateFrame:", None, True
)
def applicationShouldTerminateAfterLastWindowClosed_(self, sender):
return True
def applicationWillTerminate_(self, notification):
if hasattr(self, 'cap') and self.cap.isOpened():
self.cap.release()
def updateFrame_(self, timer):
if hasattr(self, 'cap') and self.cap.isOpened():
ret, frame = self.cap.read()
if ret:
# Convert BGR to RGB
rgb_frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
# Convert to NSImage
height, width, channels = rgb_frame.shape
bytes_per_line = channels * width
# Create BitmapRep
bitmap_rep = NSBitmapImageRep.alloc().initWithBitmapDataPlanes_pixelsWide_pixelsHigh_bitsPerSample_samplesPerPixel_hasAlpha_isPlanar_colorSpaceName_bytesPerRow_bitsPerPixel_(
None, width, height, 8, 3, False, False, "NSDeviceRGBColorSpace", bytes_per_line, 24
)
# Copy data
bitmap_data = bitmap_rep.bitmapData()
# We need to copy the bytes. This is the PyObjC way to write to the buffer requires a bit of care.
# A safer/easier way with PIL:
image = Image.fromarray(rgb_frame)
img_data = image.tobytes()
# Low-level memory copy might be tricky in pure python/objc without unsafe pointers.
# Alternative: Use PIL to save to memory buffer (TIFF/PNG) and load NSImage from data.
# This is slightly slower but safer and easier in Python.
import io
# Using PPM format is fast (uncompressed)
header = f"P6 {width} {height} 255 ".encode()
data = header + rgb_frame.tobytes()
ns_data = objc.lookUpClass("NSData").dataWithBytes_length_(data, len(data))
ns_image = NSImage.alloc().initWithData_(ns_data)
self.image_view.setImage_(ns_image)
def captureClicked_(self, sender):
print("Capture clicked")
if __name__ == "__main__":
app = NSApplication.sharedApplication()
delegate = ItemSenseApp.alloc().init()
app.setDelegate_(delegate)
NSApp.activateIgnoringOtherApps_(True)
app.run()